© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142230
    Prev
    Next
    INDEX
    Explanations

    potential, heal, left, debug, French, dialects, report, next

    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_0_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
    מ
    0.56
     lacquer
    0.54
     subtract
    0.54
    л
    0.54
     psychiatric
    0.53
    nament
    0.52
     organize
    0.52
     confid
    0.50
     plant
    0.49
     persuade
    0.49
    POSITIVE LOGITS
    䨪
    0.50
    isci
    0.48
    ტიკ
    0.47
    აშ
    0.46
    暴
    0.44
    荲
    0.44
    வெ
    0.44
    리스
    0.44
    იდან
    0.42
    ुभ
    0.42
    Activations Density 0.000%

    No Known Activations