© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157785
    Prev
    Next
    INDEX
    Explanations

    boolean default

    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_2_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
    йын
    1.13
    1.12
    '।
    1.08
    ো
    1.02
     surgir
    1.00
    <0xA5>
    0.98
    ின்
    0.98
    يته
    0.97
    тта
    0.96
     তার
    0.93
    POSITIVE LOGITS
    0
    1.88
     the
    1.62
     from
    1.49
     with
    1.45
    with
    1.29
    the
    1.23
    by
    1.23
    ments
    1.20
    .
    1.20
    for
    1.16
    Activations Density 0.000%

    No Known Activations