© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37459
    Prev
    Next
    INDEX
    Explanations

    bomb / bombing / bomb-making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    1.13
    -
    0.99
    }
    0.91
    M
    0.89
    C
    0.86
    *
    0.84
    S
    0.82
    R
    0.81
    D
    0.78
    the
    0.77
    POSITIVE LOGITS
     Bom
    0.95
     bom
    0.88
    Bom
    0.88
    ية
    0.86
     бом
    0.86
     bombs
    0.85
     bomb
    0.80
     Bomb
    0.77
     bombing
    0.74
    bom
    0.69
    Activations Density 0.022%

    No Known Activations