© 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. 60111
    Prev
    Next
    INDEX
    Explanations

    trapper

    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
    но
    1.25
    С
    1.20
    ла
    1.18
    '
    1.16
    ’
    1.14
    ور
    1.11
    П
    1.10
    ра
    1.09
    ри
    1.09
    га
    1.09
    POSITIVE LOGITS
     for
    1.49
     at
    1.13
    л
    1.09
    er
    0.97
    i
    0.92
     recob
    0.91
     צריך
    0.90
    ח
    0.90
    する
    0.86
     אפ
    0.84
    Activations Density 0.002%

    No Known Activations