© 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. 7291
    Prev
    Next
    INDEX
    Explanations

    mentions of bands and musical performances

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'practice'

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

    music/bands

    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
     disambiguazione
    -0.60
    CppMethod
    -0.58
     stereo
    -0.57
     spoken
    -0.56
    Termin
    -0.56
    sidemargin
    -0.55
     noDo
    -0.55
     terminals
    -0.55
     שוליים
    -0.55
    Tikang
    -0.54
    POSITIVE LOGITS
     practice
    0.48
     Packs
    0.48
    oció
    0.48
    Practi
    0.48
    write
    0.47
    Practice
    0.47
     detención
    0.46
     practicing
    0.44
     write
    0.44
     práctica
    0.44
    Activations Density 2.391%

    No Known Activations