© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199422
    Prev
    Next
    INDEX
    Explanations

    SVG shapes and attributes

    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_27_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
     bak
    0.38
     bring
    0.37
    fact
    0.37
    *
    0.37
    basic
    0.36
    bak
    0.36
     snaps
    0.36
     add
    0.36
    Basic
    0.35
     terse
    0.35
    POSITIVE LOGITS
     Đế
    0.40
    шкин
    0.39
     Patienten
    0.38
     Бог
    0.38
    本店
    0.38
     Ararat
    0.38
     Calvert
    0.37
    <unused68>
    0.37
    世紀
    0.37
     Balfour
    0.37
    Activations Density 0.000%

    No Known Activations