© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11648
    Prev
    Next
    INDEX
    Explanations

    a mix of capitalized initials, administrative and geographical terms, names, and the intensifier "very"

    oai_token-act-pair · gemini-2.0-flash

    technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AutoresizingMask
    -0.59
     sī
    -0.55
    setFont
    -0.48
    ̍t
    -0.48
    MarshalTo
    -0.46
    aarrggbb
    -0.46
     nos
    -0.46
    ptonshire
    -0.44
    rénées
    -0.44
     broadest
    -0.44
    POSITIVE LOGITS
    ftagPool
    0.56
    ecap
    0.52
     متحده
    0.52
     Paglinawan
    0.52
     vectorielle
    0.52
    StructEnd
    0.51
    ulisan
    0.51
    BooleanField
    0.51
    ſelf
    0.50
     marquées
    0.50
    Activations Density 0.489%

    No Known Activations