© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215527
    Prev
    Next
    INDEX
    Explanations

    edgy or edgewise

    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_5_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
    بی
    0.59
    ओं
    0.56
     (
    0.55
     foyer
    0.54
    ก็
    0.54
     microstructure
    0.53
    וס
    0.53
     calcul
    0.51
     revitalization
    0.51
    ও
    0.50
    POSITIVE LOGITS
    d
    0.95
    ين
    0.67
    {
    0.63
    r
    0.63
    ab
    0.61
    en
    0.61
    RE
    0.61
    お店
    0.59
    ด
    0.59
    S
    0.59
    Activations Density 0.000%

    No Known Activations