© 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. 199219
    Prev
    Next
    INDEX
    Explanations

    Gary & Handlen edition

    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
    en
    0.63
    ות
    0.48
    ar
    0.48
    さ
    0.46
    ities
    0.46
     supernovae
    0.46
    mars
    0.44
     Apr
    0.43
    bars
    0.43
     другие
    0.43
    POSITIVE LOGITS
     بیا
    0.52
     جديد
    0.47
    Dire
    0.46
     ≤
    0.46
     updatedAt
    0.45
    AVI
    0.45
     अवधि
    0.44
    FileSize
    0.44
    𝐴
    0.44
     ريال
    0.44
    Activations Density 0.000%

    No Known Activations