© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118660
    Prev
    Next
    INDEX
    Explanations

    dataclasses import dataclass

    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_27_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
     माँ
    0.39
    рі
    0.39
     Lü
    0.38
     Ku
    0.37
    시간
    0.37
     Corne
    0.36
     Donor
    0.36
    ൩
    0.35
     Dord
    0.34
     Clash
    0.34
    POSITIVE LOGITS
     punishing
    0.44
     चिन्ह
    0.42
     مناسب
    0.42
    onz
    0.42
    idcoin
    0.40
     geeign
    0.40
     loosely
    0.39
    მასრულ
    0.39
     ().
    0.39
    othyroidism
    0.39
    Activations Density 0.000%

    No Known Activations