© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206705
    Prev
    Next
    INDEX
    Explanations

    shit usage

    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_20_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
    !
    0.38
     первые
    0.36
     shit
    0.35
     впервые
    0.35
     sputum
    0.35
    !’
    0.35
     obliquely
    0.35
     screwed
    0.34
     inwards
    0.34
     endem
    0.33
    POSITIVE LOGITS
     unser
    0.31
    防災
    0.31
    ന്യ
    0.31
     लंबा
    0.31
    getLong
    0.31
    ት
    0.30
    ങ്ങള്‍
    0.30
    ਫ਼
    0.30
    バッテリー
    0.29
     Gray
    0.29
    Activations Density 0.000%

    No Known Activations