© 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. 11904
    Prev
    Next
    INDEX
    Explanations

    the words "Solve" or "are", some HTML tags, and math question formatting

    oai_token-act-pair · gemini-2.0-flash

    Solving/debugging

    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
    RepeatedField
    -0.54
    RectangleBorder
    -0.47
    winston
    -0.46
     viewWillAppear
    -0.46
    BASEPATH
    -0.46
    marginHorizontal
    -0.45
    yntaxException
    -0.45
     AssemblyCulture
    -0.43
    promise
    -0.41
    umente
    -0.40
    POSITIVE LOGITS
    ymce
    0.67
    estris
    0.58
    Transport
    0.56
     Roskov
    0.56
     blessés
    0.53
    talet
    0.53
    Carriera
    0.53
     Transport
    0.53
     indépendant
    0.53
     Stay
    0.52
    Activations Density 0.819%

    No Known Activations