© 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. 45043
    Prev
    Next
    INDEX
    Explanations

    John names

    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
     a
    0.72
    in
    0.65
     αριθ
    0.59
    }_{
    0.58
     dàng
    0.58
    widetilde
    0.53
    Grid
    0.52
     Ва
    0.52
     في
    0.52
     fijn
    0.52
    POSITIVE LOGITS
    ط
    0.63
    </h5>
    0.61
    vinced
    0.59
    <0x80>
    0.59
    </h4>
    0.58
    </h3>
    0.57
    y
    0.57
    αι
    0.55
    isée
    0.55
     exuber
    0.54
    Activations Density 0.000%

    No Known Activations