© 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
    2. Gemma-3-27B-IT
    3. 32-GEMMASCOPE-2-TRANSCODER-262K
    4. 237875
    Prev
    Next
    INDEX
    Explanations

    presume, interpret, protect

    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_32_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
     carefully
    0.45
     gently
    0.40
     brew
    0.39
    marg
    0.38
     핵
    0.38
     presum
    0.38
     wisely
    0.37
     cautiously
    0.36
     Aspen
    0.36
     Dury
    0.36
    POSITIVE LOGITS
    盥
    0.47
     нередко
    0.40
    矯正
    0.36
    NSMutableArray
    0.35
    cheng
    0.35
     एना
    0.35
    atherapy
    0.35
    ෲ
    0.35
     நா
    0.34
    isdigit
    0.34
    Activations Density 0.000%

    No Known Activations