© 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. 159060
    Prev
    Next
    INDEX
    Explanations

    Kremer, Krebs, Kremlin, Kreng

    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
    ll
    0.92
    revalidator
    0.88
    فاع
    0.87
    ("/");
    0.86
    razione
    0.86
    inį
    0.85
    ಷ್ಯ
    0.85
     ብዙውን
    0.84
    getInstance
    0.84
    les
    0.82
    POSITIVE LOGITS
     are
    2.03
     an
    1.49
     was
    1.48
    are
    1.48
    ü
    1.45
    ING
    1.44
     to
    1.37
    ED
    1.37
     as
    1.30
     it
    1.28
    Activations Density 0.000%

    No Known Activations