© 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. 12800
    Prev
    Next
    INDEX
    Explanations

    language related to supporting, helping, and using resources.

    oai_token-act-pair · gemini-2.0-flash

    acknowledgements

    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
     nahilalakip
    -0.92
     виправивши
    -0.87
    <bos>
    -0.81
    sizeCache
    -0.76
     Administrativna
    -0.75
     FetchType
    -0.73
     <=",
    -0.72
    Tikang
    -0.71
    onavir
    -0.71
    endphp
    -0.69
    POSITIVE LOGITS
     generously
    0.46
    gah
    0.45
    μον
    0.43
    omon
    0.43
     unknowingly
    0.42
    CEPT
    0.42
    photobucket
    0.41
    みな
    0.41
     campion
    0.41
    enumi
    0.41
    Activations Density 1.942%

    No Known Activations