© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142933
    Prev
    Next
    INDEX
    Explanations

    Sunny Meadow

    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
    .
    1.49
    した
    1.32
    ates
    1.20
    ご
    1.16
    ored
    1.13
    して
    1.11
    ০০
    1.11
    us
    1.10
    ulated
    1.09
    する
    1.07
    POSITIVE LOGITS
    t
    2.52
    ก
    1.99
    ם
    1.88
    n
    1.77
    sı
    1.74
    m
    1.73
    ן
    1.66
    ين
    1.59
    tt
    1.55
    h
    1.47
    Activations Density 0.000%

    No Known Activations