© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6258
    Prev
    Next
    INDEX
    Explanations

    text discussing the history of slavery, especially involving race.

    oai_token-act-pair · gemini-2.0-flash

    slave

    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
     Signalez
    -0.63
    RetentionPolicy
    -0.61
    IActionResult
    -0.57
    HomeAsUpEnabled
    -0.56
    NameInMap
    -0.56
     AspNetCore
    -0.55
    tanleria
    -0.54
     ExecuteAsync
    -0.54
    struts
    -0.54
     оригіналу
    -0.53
    POSITIVE LOGITS
    migrationBuilder
    0.58
    पया
    0.50
    mixing
    0.49
    znál
    0.47
    kond
    0.47
    Jeografia
    0.47
    FieldBuilder
    0.46
     Union
    0.46
     Loyal
    0.46
    Cred
    0.45
    Activations Density 2.505%

    No Known Activations