© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53235
    Prev
    Next
    INDEX
    Explanations

    academic writing context

    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
    PIT
    0.38
    miers
    0.37
    ET
    0.37
    EX
    0.36
    RETURNTRANSFER
    0.36
    imit
    0.36
     LUMPUR
    0.36
    ሂ
    0.36
    Threshold
    0.36
    IAT
    0.35
    POSITIVE LOGITS
    鵡
    0.39
     Socket
    0.37
     আহ্বায়ক
    0.37
     desenho
    0.37
    畫
    0.37
    繪
    0.36
     Terms
    0.36
    いただく
    0.36
     রাজাকার
    0.36
     drawings
    0.35
    Activations Density 0.007%

    No Known Activations