© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14521
    Prev
    Next
    INDEX
    Explanations

    defining precise purpose

    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_13_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
     K
    0.61
     both
    0.58
     plan
    0.57
     apologise
    0.56
     commence
    0.56
     yard
    0.55
    Yard
    0.55
     point
    0.54
     spade
    0.54
     Q
    0.53
    POSITIVE LOGITS
    serverResponse
    0.53
     لاکھ
    0.52
     высокая
    0.51
    诲
    0.50
     দাব
    0.50
     Certificate
    0.49
    罾
    0.48
    РИ
    0.48
     Theological
    0.48
    chaoxing
    0.48
    Activations Density 0.000%

    No Known Activations