© 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. 54233
    Prev
    Next
    INDEX
    Explanations

    selecting one

    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
     দুর্ঘটনা
    0.38
    ితో
    0.35
     деца
    0.34
    ompany
    0.34
     puluh
    0.34
    àng
    0.33
     మధ్య
    0.33
    祹
    0.33
     ойношот
    0.33
     जिससे
    0.33
    POSITIVE LOGITS
     one
    1.09
     một
    0.96
     isang
    0.93
     एक
    0.88
    一个
    0.86
     একটি
    0.85
     yksi
    0.84
     ஒரு
    0.84
     jednego
    0.84
    一种
    0.83
    Activations Density 0.037%

    No Known Activations