© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6542
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to publications, like page, chapter, or volume

    oai_token-act-pair · gemini-2.0-flash

    say period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     numberOfRows
    -0.85
     beginnetje
    -0.85
     saites
    -0.79
    IntoConstraints
    -0.75
    oa̍t
    -0.67
     Roskov
    -0.66
    Portály
    -0.63
    StructEnd
    -0.61
    Portail
    -0.61
    enterOuterAlt
    -0.60
    POSITIVE LOGITS
     linkovi
    0.44
    OOTDTY
    0.44
    -------
    0.42
    UnitTesting
    0.39
    arelli
    0.36
    PORTE
    0.36
    itación
    0.36
    ensement
    0.36
    schild
    0.35
     mời
    0.34
    Activations Density 1.332%

    No Known Activations