© 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. 88223
    Prev
    Next
    INDEX
    Explanations

    Bayern Munich

    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
    6
    0.85
    9
    0.76
    5
    0.72
    ال
    0.68
    7
    0.66
    8
    0.62
    ல்லாம்
    0.62
    鲳
    0.61
    4
    0.61
    ED
    0.60
    POSITIVE LOGITS
    i
    0.74
    <0x0D>
    0.69
    </h4>
    0.69
    </h3>
    0.66
    ні
    0.64
    </i>
    0.63
    ಿ
    0.63
    ে
    0.62
    ೆ
    0.61
    em
    0.59
    Activations Density 0.000%

    No Known Activations