© 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. 15500
    Prev
    Next
    INDEX
    Explanations

    words related to genetic frequency and seasonal traits, especially names of seasons, in academic language

    oai_token-act-pair · gemini-2.0-flash

    allele

    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
    parsedMessage
    -0.76
    EndContext
    -0.72
    setVerticalGroup
    -0.71
    RenderAtEndOf
    -0.71
     TestBed
    -0.67
    StructEnd
    -0.65
    SourceChecksum
    -0.65
    CodeAttribute
    -0.64
     समीक्षक
    -0.64
    AlterField
    -0.63
    POSITIVE LOGITS
     Daya
    0.56
     eccl
    0.55
     cadrul
    0.55
     Geraadpleegd
    0.54
    lück
    0.53
    ksy
    0.51
    petto
    0.50
    inea
    0.49
     flora
    0.48
    Adop
    0.47
    Activations Density 4.779%

    No Known Activations