© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1268
    Prev
    Next
    INDEX
    Explanations

    checks and compares

    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_39_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
    permission
    0.31
    setMaximum
    0.29
    PERMISSION
    0.28
    stige
    0.28
    য়ো
    0.28
    冋
    0.27
     Permission
    0.27
    stead
    0.27
     شراب
    0.27
    釀
    0.27
    POSITIVE LOGITS
    onitrile
    0.33
     perform
    0.32
     performs
    0.31
     pop
    0.30
    心得
    0.29
     performing
    0.29
     dere
    0.29
     radios
    0.28
     genes
    0.28
     benefitted
    0.28
    Activations Density 0.495%

    No Known Activations