© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 87308
    Prev
    Next
    INDEX
    Explanations

    waste reduction and diversion

    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_18_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
    teis
    0.27
    _{
    0.25
    舅
    0.25
    dra
    0.25
    shad
    0.25
     Airways
    0.25
    역
    0.25
    in
    0.24
    ளா
    0.23
    SCO
    0.23
    POSITIVE LOGITS
     вони
    0.33
    谧
    0.32
     Noetherian
    0.31
    正确
    0.31
     sbagli
    0.30
     AgNO
    0.30
     df
    0.29
     ဒါ
    0.29
     dieta
    0.29
     ദി
    0.29
    Activations Density 0.002%

    No Known Activations