© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2589
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "pic," possibly in the context of an image or a network

    oai_token-act-pair · gemini-2.0-flash

    tokens related to "pic" or pictures

    np_token-act-pair-logits · gpt-4o-mini

    pic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     AssemblyCulture
    -0.91
     BoxFit
    -0.85
    XmlAccessorType
    -0.81
    )";
    -0.77
     myſelf
    -0.77
    Personensuche
    -0.76
    دانشنامهٔ
    -0.76
    webElement
    -0.74
    IsContent
    -0.73
    CloseOperation
    -0.73
    POSITIVE LOGITS
     palvel
    0.39
    book
    0.37
    abestanden
    0.36
     électroniques
    0.36
     geschlossen
    0.35
    Hidden
    0.35
     verteilt
    0.35
     rū
    0.35
     náv
    0.34
     gorro
    0.33
    Activations Density 0.374%

    No Known Activations