© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120360
    Prev
    Next
    INDEX
    Explanations

    follow or join

    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_27_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
    占用
    0.45
     suman
    0.45
     COLLISIONS
    0.43
    ওনা
    0.41
    spacerItem
    0.41
    丷
    0.41
     realizzata
    0.40
    额外的
    0.40
     kucch
    0.40
     multiplicado
    0.39
    POSITIVE LOGITS
    脱
    0.41
     rejoined
    0.38
    ソ
    0.38
     reconnect
    0.38
    采用
    0.37
     disconnect
    0.37
     folgt
    0.37
    跟随
    0.36
    表
    0.36
     follows
    0.36
    Activations Density 0.018%

    No Known Activations