© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214931
    Prev
    Next
    INDEX
    Explanations

    k or ke followed by punctuation

    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_5_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
    ن
    1.49
    ام
    1.38
    ب
    1.30
    of
    1.10
    ac
    1.09
    ون
    1.03
    از
    1.02
    ala
    1.01
     النمو
    1.01
    ات
    0.98
    POSITIVE LOGITS
     I
    1.35
    できます
    1.05
    ların
    0.99
     It
    0.97
    U
    0.93
    回の
    0.92
    ட்
    0.91
    у
    0.90
    ı
    0.89
     diminu
    0.89
    Activations Density 0.000%

    No Known Activations