© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59991
    Prev
    Next
    INDEX
    Explanations

    bombs are dangerous

    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_2_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
    ت
    1.80
    d
    1.66
    dü
    1.35
    ле
    1.28
    ले
    1.23
    la
    1.23
    dob
    1.20
    ді
    1.19
    dj
    1.16
     три
    1.13
    POSITIVE LOGITS
     a
    1.13
    </h3>
    1.04
    have
    1.03
    ↵
    1.02
    로
    1.02
     A
    1.02
    </em>
    0.91
     M
    0.89
    <0x0D>
    0.89
     D
    0.89
    Activations Density 0.000%

    No Known Activations