© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61065
    Prev
    Next
    INDEX
    Explanations

    say ':'

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    ים
    0.63
    ς
    0.51
    s
    0.47
    ی
    0.47
    ों
    0.43
    sill
    0.43
    ের
    0.42
    ы
    0.41
    いる
    0.40
    trades
    0.38
    POSITIVE LOGITS
    elf
    0.94
    ELF
    0.84
    OL
    0.79
    OME
    0.79
    eem
    0.77
    ome
    0.76
    ometimes
    0.75
    OURCES
    0.75
    ET
    0.75
    UCH
    0.73
    Activations Density 0.000%

    No Known Activations