© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9589
    Prev
    Next
    INDEX
    Explanations

    words or symbols used in academic papers

    oai_token-act-pair · gemini-2.0-flash

    academic/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     fj
    -0.41
     faute
    -0.40
    прав
    -0.40
     Indemnity
    -0.39
     múl
    -0.39
    ToolStrip
    -0.38
     crankshaft
    -0.38
    fw
    -0.37
    mba
    -0.35
    역
    -0.35
    POSITIVE LOGITS
    ⓧ
    0.88
     Monfieur
    0.84
     houſe
    0.84
     myſelf
    0.82
     itſelf
    0.80
     Efq
    0.80
     ſeveral
    0.75
     Reſ
    0.74
     purpoſe
    0.73
     Majefty
    0.72
    Activations Density 4.730%

    No Known Activations