© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139943
    Prev
    Next
    INDEX
    Explanations

    Gemini exchange

    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_12_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
    𝚗
    0.43
    or
    0.43
    en
    0.42
    developers
    0.42
     zouden
    0.41
    okine
    0.41
    Ŝ
    0.40
     seraient
    0.39
    ？」
    0.39
     වශ
    0.39
    POSITIVE LOGITS
     at
    0.52
    ห
    0.49
     $
    0.48
    м
    0.47
     uso
    0.47
    хь
    0.46
    Г
    0.45
    _
    0.45
    П
    0.43
     &
    0.43
    Activations Density 0.000%

    No Known Activations