© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142729
    Prev
    Next
    INDEX
    Explanations

    CHAR type in programming

    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_0_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
     I
    1.55
     immor
    1.42
     ошибок
    1.26
    お店
    1.25
     drugih
    1.25
     второй
    1.20
     نکات
    1.20
     zmiany
    1.20
     liczb
    1.19
     август
    1.18
    POSITIVE LOGITS
    of
    2.20
    я
    1.68
    ة
    1.59
    ن
    1.55
     of
    1.52
    וס
    1.48
    ك
    1.47
    อร์
    1.45
    اً
    1.45
    ν
    1.44
    Activations Density 0.000%

    No Known Activations