© 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. 62250
    Prev
    Next
    INDEX
    Explanations

    Basilisk, Basilica, Basil

    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
    एस
    1.19
    y
    1.14
    ays
    1.09
    ع
    1.09
    ul
    1.05
    n
    1.01
    il
    0.95
    েরা
    0.92
    та
    0.90
    ation
    0.88
    POSITIVE LOGITS
    يل
    1.39
    يف
    1.34
    ב
    1.21
    ጨማሪ
    1.09
    אר
    1.03
    قيق
    1.03
    ру
    1.02
    راهيم
    1.00
     možnosti
    0.98
    રી
    0.97
    Activations Density 0.000%

    No Known Activations