© 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. 16055
    Prev
    Next
    INDEX
    Explanations

    a wide range of seemingly unrelated things including bible verses, chemical formulas, and various miscellaneous symbols and punctuation.

    oai_token-act-pair · 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
    -
    -0.61
    EndContext
    -0.53
    ,
    -0.52
    posedge
    -0.48
    (
    -0.47
     članak
    -0.46
    )
    -0.45
    ⓧ
    -0.45
    Życiorys
    -0.44
    的主
    -0.44
    POSITIVE LOGITS
     Monfieur
    0.85
     Cæsar
    0.84
     Reſ
    0.82
     ſeveral
    0.81
     pleaſure
    0.80
     Efq
    0.79
     Theſe
    0.79
     leaſt
    0.77
     itſelf
    0.77
     raiſ
    0.74
    Activations Density 6.857%

    No Known Activations