© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 215
    Prev
    Next
    INDEX
    Explanations

    acknowledging agreement

    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_40_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
    ymal
    0.28
     wdir
    0.28
     Đoàn
    0.27
     Elevations
    0.26
    ()">
    0.26
     dems
    0.26
    팸
    0.26
    ();
    0.25
     Skeleton
    0.25
    ☯
    0.25
    POSITIVE LOGITS
     away
    0.31
    away
    0.31
    quel
    0.30
    Ap
    0.29
    Alright
    0.29
     overwhelmingly
    0.29
    straight
    0.28
     Away
    0.28
    ไอ
    0.27
     Oo
    0.27
    Activations Density 0.217%

    No Known Activations