© 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. 9175
    Prev
    Next
    INDEX
    Explanations

    text related to police criminal records, immigration, and biometric data

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to criminal records

    np_token-act-pair-logits · gpt-4o-mini
    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
    帖最后由
    -0.65
    enterOuterAlt
    -0.52
     BoxFit
    -0.50
    adə
    -0.50
     ExecuteAsync
    -0.49
     للاسماء
    -0.48
     TextAppearance
    -0.46
    artament
    -0.46
    tagHelperRunner
    -0.45
     accessori
    -0.44
    POSITIVE LOGITS
     lenker
    0.67
    BASEPATH
    0.64
    ExecuteReader
    0.62
    ServletException
    0.60
     Crossing
    0.57
    linalg
    0.54
    adaptiveStyles
    0.53
     HttpNotFound
    0.53
    InitVars
    0.53
     doPost
    0.52
    Activations Density 1.109%

    No Known Activations