© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144105
    Prev
    Next
    INDEX
    Explanations

    abused their power

    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_0_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
     on
    1.86
     of
    1.48
     for
    1.41
    ۹
    1.39
     Ә
    1.32
     ऑन
    1.30
    行う
    1.27
     (
    1.21
    ८
    1.19
    含ま
    1.18
    POSITIVE LOGITS
    u
    2.27
    in
    1.87
    w
    1.72
    ur
    1.58
    r
    1.55
    p
    1.52
    ul
    1.45
    the
    1.45
    v
    1.33
    re
    1.27
    Activations Density 0.000%

    No Known Activations