© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1594
    Prev
    Next
    INDEX
    Explanations

    words and phrases mostly related to government and scientific studies

    oai_token-act-pair · gemini-2.0-flash

    Deep State

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    errHandler
    -0.57
    Portail
    -0.52
    Koordinaten
    -0.47
    Portale
    -0.46
     Chwiliwch
    -0.46
    Personensuche
    -0.45
     Seeder
    -0.44
     Encu
    -0.44
    MENAFN
    -0.44
    WebElementEntity
    -0.43
    POSITIVE LOGITS
    "}")
    0.71
    codehaus
    0.63
    enderror
    0.61
    +};
    0.60
    плуата
    0.59
     preocupes
    0.57
    ]<<"
    0.56
    SFER
    0.56
    částí
    0.56
    ,:);
    0.56
    Activations Density 21.283%

    No Known Activations