© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77355
    Prev
    Next
    INDEX
    Explanations

    Chronic, Certain

    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_31_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
    CHEAT
    0.36
     Tru
    0.35
    deepcopy
    0.35
    考える
    0.34
     Knowles
    0.34
     Trick
    0.33
    ên
    0.33
    濘
    0.33
    वाइड
    0.33
     জানার
    0.33
    POSITIVE LOGITS
    Bever
    0.38
     regeneration
    0.36
    ेटिक
    0.36
    なし
    0.36
     certain
    0.35
     stresses
    0.34
     draftsman
    0.34
    efeuille
    0.33
     expired
    0.33
     royalty
    0.33
    Activations Density 0.033%

    No Known Activations