© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112004
    Prev
    Next
    INDEX
    Explanations

    digestion

    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
     for
    1.49
    ן
    1.38
    ла
    1.34
    ية
    1.26
    ри
    1.21
    ian
    1.09
     in
    1.06
    ס
    1.02
    )$
    0.93
    东西
    0.90
    POSITIVE LOGITS
    માં
    1.23
    К
    1.12
    sp
    1.07
    to
    1.03
    ف
    1.02
    igers
    1.00
    با
    0.98
    но
    0.97
    na
    0.96
    сет
    0.96
    Activations Density 0.001%

    No Known Activations