© 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. 60360
    Prev
    Next
    INDEX
    Explanations

    Montmartre

    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
    z
    0.42
     mathvariant
    0.39
     একত্রে
    0.39
     personel
    0.38
     exponents
    0.38
    zani
    0.37
    marginX
    0.37
     guarantees
    0.37
     biel
    0.37
    ¯</
    0.37
    POSITIVE LOGITS
    ым
    0.42
    ният
    0.39
     et
    0.38
    ctions
    0.37
    OMA
    0.36
    рия
    0.35
    Acet
    0.35
    Dec
    0.34
    აციის
    0.34
    ंह
    0.34
    Activations Density 0.000%

    No Known Activations