© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10314
    Prev
    Next
    INDEX
    Explanations

    code snippets that include bracketed segments, returns, and accessors

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    SuccessListener
    -0.64
     виправивши
    -0.58
    ToAction
    -0.57
     scolaires
    -0.57
    EndContext
    -0.56
    حياته
    -0.55
     useRouter
    -0.54
     iconFacebook
    -0.54
    XmlAccessType
    -0.54
    таратура
    -0.54
    POSITIVE LOGITS
    featureID
    0.65
    SOUNDBITE
    0.63
    setVerticalGroup
    0.62
    HideFlags
    0.57
     BorderSide
    0.53
    <bos>
    0.52
    setViewportView
    0.48
     GeoNames
    0.48
    LookAnd
    0.46
    Vidite
    0.44
    Activations Density 0.688%

    No Known Activations