© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12302
    Prev
    Next
    INDEX
    Explanations

    conversational filler and hedging language in opinionated statements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Hentet
    -0.47
    ots
    -0.47
     apostles
    -0.46
    jej
    -0.46
    chi
    -0.44
     прово
    -0.43
    not
    -0.43
    兆
    -0.43
     indeb
    -0.42
    devtools
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    úsqueda
    0.60
    featureID
    0.60
    enumi
    0.59
    déric
    0.57
     Administrativna
    0.55
    casm
    0.55
    webElementGuid
    0.55
    <?
    0.54
     XXIV
    0.53
    Activations Density 2.315%

    No Known Activations