© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1045
    Prev
    Next
    INDEX
    Explanations

    the word "including" and lists marked with colons, bullets, or asterisks.

    oai_token-act-pair · gemini-2.0-flash

    lists introduced by colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     المعيارى
    -0.57
    toHexString
    -0.57
     vPvB
    -0.57
    Код
    -0.54
    ("$.
    -0.52
     Hap
    -0.52
    HtmlAttribute
    -0.51
    IVEREF
    -0.51
     géographique
    -0.49
    хіво
    -0.49
    POSITIVE LOGITS
    principalTable
    0.59
    oglobulin
    0.55
    ئه
    0.53
    herin
    0.53
     combineReducers
    0.52
     suivants
    0.52
    following
    0.51
    ️
    0.50
     BoxDecoration
    0.50
     şun
    0.50
    Activations Density 1.144%

    No Known Activations