© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2296
    Prev
    Next
    INDEX
    Explanations

    "' or punctuation before 't'

    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_40_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
     eût
    0.23
    。</
    0.22
     oatmeal
    0.22
    ングラス
    0.22
     कोशिका
    0.22
     basaltes
    0.21
    。」
    0.21
    ristown
    0.21
     ।*
    0.21
    ডেম
    0.21
    POSITIVE LOGITS
    X
    0.25
     Inc
    0.23
    H
    0.21
     X
    0.19
     pron
    0.19
    PLIC
    0.19
     punct
    0.19
     pronounce
    0.19
     based
    0.19
     fuel
    0.19
    Activations Density 0.108%

    No Known Activations