© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199282
    Prev
    Next
    INDEX
    Explanations

    generations per year

    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_15_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
    ចិត្ត
    0.55
    akang
    0.54
    m
    0.52
    栅
    0.52
    텁
    0.51
    㡷
    0.51
    kang
    0.51
    enburg
    0.49
     京都
    0.49
    kek
    0.48
    POSITIVE LOGITS
    Ɗ
    0.53
     dimes
    0.52
     headlights
    0.52
    UEFA
    0.49
    НИЕ
    0.49
     methane
    0.49
    Investors
    0.48
     beads
    0.48
     mushroom
    0.48
     tracer
    0.48
    Activations Density 0.000%

    No Known Activations