© 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. 7238
    Prev
    Next
    INDEX
    Explanations

    dates and military units

    oai_token-act-pair · gemini-2.0-flash

    unusual or specific terms

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

    dates

    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
     July
    -1.60
     April
    -1.59
     March
    -1.58
     June
    -1.58
     October
    -1.52
     September
    -1.51
     December
    -1.47
     November
    -1.46
     January
    -1.46
     August
    -1.46
    POSITIVE LOGITS
    RectangleBorder
    0.57
    unnitel
    0.50
    tvguidetime
    0.50
    رشف
    0.49
    drawSprites
    0.48
     transférez
    0.47
     Hannibal
    0.47
    Autoritní
    0.46
    osoba
    0.46
     OFDb
    0.45
    Activations Density 0.332%

    No Known Activations