© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176088
    Prev
    Next
    INDEX
    Explanations

    on

    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_24_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
     ;
    0.32
     میلیون
    0.31
    O
    0.31
     disclosure
    0.30
     INC
    0.29
     ولكن
    0.29
    वा
    0.29
    ();
    0.28
    DATA
    0.28
     Sore
    0.28
    POSITIVE LOGITS
    胄
    0.38
     eigenes
    0.37
     geometries
    0.35
    ttemberg
    0.34
     divisi
    0.33
     merges
    0.32
    middlewares
    0.32
    VhZ
    0.32
     cameos
    0.32
     formes
    0.31
    Activations Density 0.001%

    No Known Activations