© 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. 180046
    Prev
    Next
    INDEX
    Explanations

    served as

    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
     }^{*}$
    0.43
    माग
    0.42
    нных
    0.42
    ্রে
    0.41
    Baltimore
    0.41
     sadr
    0.41
    guardo
    0.41
    unku
    0.41
    bamos
    0.40
    schlag
    0.40
    POSITIVE LOGITS
     適
    0.40
     Maxi
    0.38
     يدل
    0.38
    家
    0.38
     Pat
    0.37
    、
    0.37
    婆
    0.37
    教科
    0.37
    ，
    0.36
     Rubin
    0.35
    Activations Density 0.001%

    No Known Activations