© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1728
    Prev
    Next
    INDEX
    Explanations

    tikz code

    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_40_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
     MOT
    0.38
    不愿意
    0.38
     Willis
    0.37
    疊
    0.37
     yat
    0.36
     registries
    0.35
     UT
    0.35
     ради
    0.35
    看一下
    0.35
     Whittaker
    0.35
    POSITIVE LOGITS
    STYLE
    0.42
     STYLE
    0.40
    jq
    0.38
    <unused82>
    0.38
    ুঁ
    0.38
    শাক
    0.37
    骛
    0.36
    सदीय
    0.35
    stru
    0.34
    etil
    0.34
    Activations Density 0.000%

    No Known Activations