© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133180
    Prev
    Next
    INDEX
    Explanations

    as befitting

    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_6_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
    I
    1.31
    re
    1.21
    A
    1.13
    ל
    1.09
    f
    1.07
    H
    1.07
    الن
    1.02
    い
    1.00
    IAC
    0.98
    内
    0.98
    POSITIVE LOGITS
    ى
    1.25
    т
    1.08
    ية
    0.93
    й
    0.88
     ανα
    0.85
     δυνα
    0.84
    amp
    0.84
    ized
    0.82
    ви
    0.82
     αλλά
    0.82
    Activations Density 0.000%

    No Known Activations