© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3389
    Prev
    Next
    INDEX
    Explanations

    HTML image tags, date ranges and height/width attributes

    oai_token-act-pair · gemini-2.0-flash

    code and file contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    #+#
    -0.53
    ↩
    -0.47
     origin
    -0.45
    jsii
    -0.45
     ver
    -0.45
     öss
    -0.44
     Art
    -0.44
     Hein
    -0.43
    RIV
    -0.43
    hes
    -0.43
    POSITIVE LOGITS
    fillType
    0.61
    makeConstraints
    0.60
     gynhyrchwyd
    0.60
    ImageContext
    0.59
     calculées
    0.59
    styleType
    0.59
    зулта
    0.59
    tagHelperRunner
    0.59
     ModelExpression
    0.59
    UrlResolution
    0.58
    Activations Density 1.674%

    No Known Activations