© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196253
    Prev
    Next
    INDEX
    Explanations

    yoke

    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_4_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
    on
    1.16
    .
    1.10
    ;
    1.09
    ker
    1.06
    aj
    1.02
    ke
    1.02
    ه
    0.95
    ul
    0.93
    5
    0.92
    ut
    0.90
    POSITIVE LOGITS
    い
    1.25
    ות
    1.11
    し
    1.08
     Слова
    1.01
     Ин
    1.00
     protezione
    0.99
    ない
    0.98
    れの
    0.97
    ים
    0.97
    ので
    0.97
    Activations Density 0.000%

    No Known Activations