© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158551
    Prev
    Next
    INDEX
    Explanations

    theres atheres no

    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
    at
    1.85
    h
    1.80
    ed
    1.31
    as
    1.28
    in
    1.26
    ing
    1.23
    av
    1.20
    <0x91>
    1.20
    '
    1.17
    い
    1.17
    POSITIVE LOGITS
     ingrained
    1.13
    ון
    1.10
    UT
    1.06
    ку
    0.97
    場合は
    0.97
    צ
    0.97
    OT
    0.95
     удовлетво
    0.95
    EM
    0.95
    స్కీ
    0.92
    Activations Density 0.000%

    No Known Activations