© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12945
    Prev
    Next
    INDEX
    Explanations

    terms related to content creation, file management, and API endpoints.

    oai_token-act-pair · gemini-2.0-flash

    documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    PreExecute
    -0.63
    yaszt
    -0.56
     mati
    -0.55
     chem
    -0.54
     Krause
    -0.54
    espero
    -0.53
    engaruhi
    -0.52
     episódios
    -0.50
    umes
    -0.50
     Odo
    -0.49
    POSITIVE LOGITS
    клопе
    0.58
    лтемелер
    0.56
    Vidite
    0.56
    fjspx
    0.55
    üyada
    0.54
     CHtml
    0.52
     autorytatywna
    0.52
    addCriterion
    0.51
     semula
    0.51
    GOTREF
    0.51
    Activations Density 19.087%

    No Known Activations