© 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. 58537
    Prev
    Next
    INDEX
    Explanations

    us, thur, archer

    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
    లో
    1.34
    ع
    1.30
     (
    1.21
    কে
    1.09
    ط
    1.09
    EL
    1.07
    ت
    1.07
    كما
    1.05
     dív
    1.04
     jede
    1.03
    POSITIVE LOGITS
    ian
    1.17
    ד
    1.16
    ない
    1.07
    ל
    1.03
    ני
    1.02
    ну
    1.01
     angelic
    1.01
    ast
    1.00
    ੀ
    0.98
    ro
    0.98
    Activations Density 0.000%

    No Known Activations