© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46678
    Prev
    Next
    INDEX
    Explanations

    php code constructs

    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_3_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
    ні
    0.83
    ق
    0.83
    ని
    0.74
     Jard
    0.73
    ت
    0.71
    რება
    0.68
     I
    0.68
    ي
    0.65
    რ
    0.65
     Dessous
    0.64
    POSITIVE LOGITS
    ing
    0.82
    ad
    0.79
    ale
    0.75
    eg
    0.74
    IS
    0.73
    ang
    0.72
    ees
    0.72
     avete
    0.72
     tarafından
    0.71
    UR
    0.71
    Activations Density 0.001%

    No Known Activations