© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209962
    Prev
    Next
    INDEX
    Explanations

    шо ты or afeitado

    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_5_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
    ।
    1.55
    。
    1.36
     for
    1.23
    ।’
    1.19
    。\
    1.16
    IG
    1.12
    ።
    1.04
    0
    1.03
    RA
    1.02
     eds
    1.02
    POSITIVE LOGITS
    ק
    1.67
    л
    1.46
    я
    1.45
    し
    1.40
    д
    1.34
    earth
    1.29
    t
    1.27
    ل
    1.27
    λ
    1.27
    г
    1.27
    Activations Density 0.000%

    No Known Activations