© 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. 76199
    Prev
    Next
    INDEX
    Explanations

    human-readable file sizes

    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
     পারলে
    0.36
    Ố
    0.35
    Pad
    0.35
    licting
    0.33
     proteomics
    0.32
    BusinessType
    0.32
     MALDI
    0.32
    呚
    0.32
    Chu
    0.31
     PAD
    0.31
    POSITIVE LOGITS
     LHS
    0.57
     QH
    0.54
     LH
    0.54
     H
    0.51
    एच
    0.51
     BH
    0.48
     hydrogen
    0.48
     hydraulic
    0.47
    𝐻
    0.47
    ohyd
    0.47
    Activations Density 0.002%

    No Known Activations