© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15850
    Prev
    Next
    INDEX
    Explanations

    words, particularly in the context of scientific or technical writing, related to statistical likelihood or deviation from expectations

    oai_token-act-pair · gemini-2.0-flash

    japanese and/or chance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    +#+#
    -1.13
    tonode
    -1.04
     дописавши
    -1.03
    RetentionPolicy
    -1.00
    extAlignment
    -0.99
     Мексичка
    -0.97
    UrlResolution
    -0.96
    NUMX
    -0.96
    帖最后由
    -0.95
    mallows
    -0.94
    POSITIVE LOGITS
    ly
    0.77
    k
    0.72
     
    0.72
     How
    0.69
    p
    0.65
    pen
    0.64
    tak
    0.61
    at
    0.61
    r
    0.60
    cas
    0.59
    Activations Density 1.129%

    No Known Activations