© 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. 75926
    Prev
    Next
    INDEX
    Explanations

    description and notes

    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
     druż
    0.39
     экрана
    0.38
     együtt
    0.37
    φό
    0.36
     उमेश
    0.35
    Ά
    0.35
    AutoScale
    0.35
    ুৎ
    0.35
     haired
    0.35
     fraudulently
    0.35
    POSITIVE LOGITS
    idur
    0.42
    tim
    0.39
     विंड
    0.38
    itaires
    0.38
     sans
    0.37
    ஸ்ப
    0.37
    prav
    0.36
    ಮ
    0.36
    超過
    0.35
     रिली
    0.35
    Activations Density 0.006%

    No Known Activations