© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6427
    Prev
    Next
    INDEX
    Explanations

    words implying something happening consistently or repeatedly

    oai_token-act-pair · gemini-2.0-flash

    always

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     always
    -2.91
    always
    -2.58
     Always
    -2.34
    Always
    -2.34
     siempre
    -2.08
     sempre
    -2.08
     ALWAYS
    -2.06
    ALWAYS
    -1.87
     selalu
    -1.86
     alltid
    -1.84
    POSITIVE LOGITS
    FieldBuilder
    0.71
    tagHelperRunner
    0.67
     Pliocene
    0.60
     Económica
    0.56
    endphp
    0.56
     Профиль
    0.56
     lâm
    0.54
     Coarse
    0.52
     âgé
    0.52
     horseshoe
    0.52
    Activations Density 2.333%

    No Known Activations