© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42476
    Prev
    Next
    INDEX
    Explanations

    most people

    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_3_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
    ו
    1.24
    و
    0.85
    ה
    0.73
    ه
    0.70
    המ
    0.63
    }");
    0.63
    -
    0.63
    /
    0.60
    用い
    0.58
    (...)
    0.58
    POSITIVE LOGITS
    c
    0.82
     is
    0.80
    g
    0.77
     as
    0.74
     are
    0.74
    k
    0.73
    ad
    0.73
    。
    0.72
    ED
    0.71
     on
    0.71
    Activations Density 0.002%

    No Known Activations