© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8387
    Prev
    Next
    INDEX
    Explanations

    a long sequence of tokens probably representing a music album review, giving strongest activation to the actual number of songs mentioned in the review

    oai_token-act-pair · gemini-2.0-flash

    references to music tracks

    np_token-act-pair-logits · gpt-4o-mini

    Music tracks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.54
    tvguidetime
    -0.53
    waitKey
    -0.50
     autorytatywna
    -0.49
    opardy
    -0.48
     ويكيپيديا
    -0.47
     sing
    -0.47
    amoan
    -0.47
    Ārējās
    -0.46
    hasMoreElements
    -0.46
    POSITIVE LOGITS
     tracks
    0.79
     track
    0.77
     TRACK
    0.67
    BeginContext
    0.67
     cortes
    0.66
    WebElementEntity
    0.64
     cuts
    0.63
    :✨
    0.62
     Track
    0.62
    track
    0.62
    Activations Density 1.098%

    No Known Activations