© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34264
    Prev
    Next
    INDEX
    Explanations

    red pepper flakes

    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_3_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
    с
    0.91
    ール
    0.89
    ння
    0.87
     και
    0.76
     और
    0.72
     и
    0.71
    ви
    0.70
    но
    0.63
    д
    0.63
    及び
    0.62
    POSITIVE LOGITS
    6
    1.00
    9
    0.93
    7
    0.91
    8
    0.89
    ر
    0.81
    </h2>
    0.80
    ין
    0.78
    5
    0.72
    ↵
    0.68
    OC
    0.67
    Activations Density 0.009%

    No Known Activations