© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108454
    Prev
    Next
    INDEX
    Explanations

    governs or governed

    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_1_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
     to
    1.52
    ing
    1.13
    (
    1.09
    ,
    1.02
     a
    1.01
    ີ່
    0.93
     of
    0.89
    νού
    0.87
    jection
    0.85
     the
    0.85
    POSITIVE LOGITS
    ي
    2.30
    i
    1.63
    י
    1.45
    يّ
    1.29
    ი
    1.23
    ه
    1.23
    지
    1.23
    يلا
    1.16
    }$.
    1.14
    ون
    1.12
    Activations Density 0.001%

    No Known Activations