© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31569
    Prev
    Next
    INDEX
    Explanations

    grade review outcomes

    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_40_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
     give
    1.53
     giving
    1.52
    Give
    1.52
     Give
    1.50
    give
    1.45
    給
    1.43
     Giving
    1.38
    Giving
    1.33
    giving
    1.32
     GIVE
    1.31
    POSITIVE LOGITS
    حي
    0.37
     Rei
    0.35
    رہ
    0.35
     banda
    0.35
    条
    0.33
     replica
    0.33
    गंज
    0.33
    Copies
    0.33
    帯
    0.33
     तिलावत
    0.33
    Activations Density 0.050%

    No Known Activations