© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2207
    Prev
    Next
    INDEX
    Explanations

    words related to organizations and rankings

    oai_token-act-pair · gemini-2.0-flash

    tokens related to software or digital products

    np_token-act-pair-logits · gpt-4o-mini

    Rankings and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     للمعارف
    -0.88
    RetentionPolicy
    -0.84
    didSet
    -0.73
    endpush
    -0.71
    ModelSerializer
    -0.70
     initComponents
    -0.68
    "},
    -0.67
     endwhile
    -0.67
    OrNil
    -0.67
    KommentareTeilen
    -0.65
    POSITIVE LOGITS
     testemun
    0.40
    ,
    0.38
    Zum
    0.37
    jemahan
    0.37
    То
    0.37
     ide
    0.36
     fazendo
    0.36
     artesanato
    0.36
     fork
    0.36
     Fork
    0.36
    Activations Density 9.056%

    No Known Activations