© 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. 4966
    Prev
    Next
    INDEX
    Explanations

    hateful, anti-feminist rhetoric

    oai_token-act-pair · gemini-2.0-flash

    rape and abuse

    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
    Pty
    -0.47
     Breaking
    -0.46
     parameters
    -0.45
     breaking
    -0.45
    Salmo
    -0.44
    &=&
    -0.43
    bergh
    -0.43
    viewtopic
    -0.43
     sliding
    -0.43
    grit
    -0.43
    POSITIVE LOGITS
    Personensuche
    0.92
    ніципа
    0.69
     resourceCulture
    0.66
    -------------</
    0.65
    StructEnd
    0.64
    sidemargin
    0.63
    RegressionTest
    0.63
    جغرافيا
    0.59
     sanitaires
    0.57
    OGND
    0.57
    Activations Density 12.368%

    No Known Activations