© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32154
    Prev
    Next
    INDEX
    Explanations

    escape or leave

    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_31_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
    慢
    0.42
    '...
    0.37
     slower
    0.36
     দিকের
    0.36
     Felic
    0.35
    Doesn
    0.34
    燮
    0.34
    Slow
    0.34
     Ljub
    0.33
    練
    0.33
    POSITIVE LOGITS
     Escape
    0.45
     escape
    0.44
    escape
    0.43
    ursed
    0.42
     Exit
    0.42
    exit
    0.41
    逃
    0.41
     exit
    0.41
     atmosfera
    0.40
    hot
    0.40
    Activations Density 0.022%

    No Known Activations