© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7053
    Prev
    Next
    INDEX
    Explanations

    LaTeX code environments

    oai_token-act-pair · gemini-2.0-flash

    section

    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
    ^(@)
    -0.93
    ScopeManager
    -0.81
     незавершена
    -0.77
     itſelf
    -0.75
    Sucesor
    -0.75
    Tikang
    -0.74
     kasarigan
    -0.74
     myſelf
    -0.73
    новништво
    -0.73
    (!__
    -0.73
    POSITIVE LOGITS
    of
    0.46
    esModule
    0.43
    <bos>
    0.42
    Of
    0.41
    ba
    0.41
    makeText
    0.40
    -
    0.40
    懈
    0.39
    no
    0.39
    vi
    0.39
    Activations Density 0.314%

    No Known Activations