© 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. 15111
    Prev
    Next
    INDEX
    Explanations

    right direction, questions, decisions, thing

    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
     that
    0.49
    !]
    0.48
    }:
    0.48
    I
    0.48
    L
    0.47
    !...
    0.47
    İ
    0.47
    that
    0.46
    라스
    0.46
    J
    0.46
    POSITIVE LOGITS
     ಅಂಶ
    0.58
     Fisk
    0.49
     foils
    0.48
     tính
    0.48
     primera
    0.46
    льності
    0.46
     получила
    0.46
     фактор
    0.45
     अंश
    0.44
     tenemos
    0.44
    Activations Density 0.034%

    No Known Activations