© 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. 161634
    Prev
    Next
    INDEX
    Explanations

    top priority

    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
    е
    1.34
     as
    1.29
    lerine
    1.27
     and
    1.25
    ل
    1.25
    ン
    1.23
    К
    1.23
    л
    1.18
    ۵
    1.13
     are
    1.10
    POSITIVE LOGITS
    ות
    1.13
    ,
    1.02
    تون
    0.98
    ן
    0.90
    تين
    0.89
    سى
    0.88
    تها
    0.87
    ิ
    0.87
     niin
    0.85
     smrti
    0.84
    Activations Density 0.000%

    No Known Activations