© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24955
    Prev
    Next
    INDEX
    Explanations

    say "*"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ↵↵↵↵↵↵↵
    0.41
    ↵↵↵↵↵↵
    0.39
    ↵↵↵↵↵
    0.38
     stuffing
    0.38
    Mood
    0.37
    έρα
    0.37
     uv
    0.37
    㓶
    0.37
    ObjectID
    0.36
    dote
    0.35
    POSITIVE LOGITS
     Stream
    0.45
    َالَ
    0.40
    Stream
    0.39
    και
    0.39
     आणि
    0.38
     AND
    0.38
     i
    0.37
     JUN
    0.37
     ও
    0.36
    uploaded
    0.36
    Activations Density 0.002%

    No Known Activations