© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14906
    Prev
    Next
    INDEX
    Explanations

    language related to copyright and image usage restrictions.

    oai_token-act-pair · gemini-2.0-flash

    license/copyright agreements

    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
     nahilalakip
    -0.77
     MainAxisSize
    -0.73
    醐
    -0.73
    GEBURTS
    -0.72
     ProtoMessage
    -0.71
     Roskov
    -0.71
     Efq
    -0.69
    CppMethod
    -0.69
    SourceChecksum
    -0.68
     épais
    -0.67
    POSITIVE LOGITS
     Vikipedi
    0.48
     sub
    0.48
     s
    0.46
     red
    0.41
    bigskip
    0.41
     exemp
    0.40
    monary
    0.40
    simov
    0.39
     int
    0.39
    paramref
    0.39
    Activations Density 0.454%

    No Known Activations