© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31373
    Prev
    Next
    INDEX
    Explanations

    numbers representing count

    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
    四大
    0.38
    ⑤
    0.37
     residue
    0.34
    XZ
    0.34
     vignette
    0.34
    ውን
    0.34
     مطل
    0.33
    第五
    0.33
    निश्ड
    0.33
     +"\
    0.32
    POSITIVE LOGITS
     七
    0.67
     Seven
    0.60
     tujuh
    0.59
     ஏழு
    0.57
     सात
    0.57
     семи
    0.57
     bảy
    0.56
     seven
    0.56
    Seven
    0.55
    seven
    0.53
    Activations Density 0.086%

    No Known Activations