© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3283
    Prev
    Next
    INDEX
    Explanations

    the third-person pronouns in a violent encounter

    oai_token-act-pair · gemini-2.0-flash

    offensive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    migrationBuilder
    -0.75
    consulté
    -0.63
    RectangleBorder
    -0.59
     doInBackground
    -0.57
    ReferenceEquals
    -0.54
     समीक्षाएं
    -0.53
    tribune
    -0.52
     onData
    -0.52
    +:+
    -0.51
    ագրություններ
    -0.48
    POSITIVE LOGITS
     offensive
    0.75
    offensive
    0.73
     Offensive
    0.73
     offense
    0.71
    Offensive
    0.66
     offence
    0.62
     counter
    0.61
     initiative
    0.60
     offensi
    0.59
     offensively
    0.59
    Activations Density 1.131%

    No Known Activations