© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211297
    Prev
    Next
    INDEX
    Explanations

    code completion

    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_5_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
    u
    1.64
    on
    1.26
    te
    1.25
    U
    1.23
    ak
    1.20
    er
    1.19
    R
    1.19
    Version
    1.16
    l
    1.12
    Time
    1.09
    POSITIVE LOGITS
    س
    1.60
    ی
    1.38
    ス
    1.33
     egos
    1.23
     culp
    1.13
    的光
    1.01
    ش
    1.01
    ۔
    0.98
     большие
    0.98
     goble
    0.96
    Activations Density 0.000%

    No Known Activations