© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4735
    Prev
    Next
    INDEX
    Explanations

    connections or origins, often signified by "from", "of", "in", "with," or "to".

    oai_token-act-pair · gemini-2.0-flash

    from in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    :✨
    -0.58
    featureID
    -0.55
     piele
    -0.54
     segn
    -0.52
    Bibliograf
    -0.49
    ✷
    -0.48
     Италијани
    -0.48
     žaid
    -0.46
     Wikimedijinoj
    -0.46
    sizable
    -0.46
    POSITIVE LOGITS
    ArgsConstructor
    0.65
     NSCoder
    0.64
    StandardCharsets
    0.63
    __).
    0.60
    NOPQRST
    0.60
    ]))
    0.59
    astify
    0.59
     QtGui
    0.58
    tvguidetime
    0.56
    DrawerToggle
    0.56
    Activations Density 13.156%

    No Known Activations