© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53100
    Prev
    Next
    INDEX
    Explanations

    disrupting or cut off

    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_30_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
    怒
    0.37
     전쟁
    0.36
     marah
    0.34
    తంగా
    0.34
     bisher
    0.34
    Autow
    0.33
     жесто
    0.33
    愤怒
    0.33
    승
    0.32
     jazz
    0.32
    POSITIVE LOGITS
     ที
    0.35
    egu
    0.34
     ply
    0.34
     brew
    0.34
    kotlin
    0.34
    eglasses
    0.34
     getMain
    0.33
    opening
    0.33
     Chronic
    0.33
    ടൊപ്പം
    0.32
    Activations Density 0.037%

    No Known Activations