© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12785
    Prev
    Next
    INDEX
    Explanations

    technical writing related to engineering, science, and computing, along with words indicating conclusions and proclamations.

    oai_token-act-pair · gemini-2.0-flash

    Describing actions/processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Chwiliwch
    -1.00
     snippetHide
    -0.93
     الحره
    -0.93
     MainAxisSize
    -0.91
    MigrationBuilder
    -0.91
    TypedDataSet
    -0.87
    RenderAtEndOf
    -0.85
    __':
    -0.84
    abetes
    -0.83
    
    -0.82
    POSITIVE LOGITS
     all
    0.40
     led
    0.39
     inform
    0.38
    so
    0.36
    ă
    0.36
     put
    0.35
     finas
    0.35
     encontraba
    0.34
     salvar
    0.34
    ,
    0.34
    Activations Density 33.479%

    No Known Activations