© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32954
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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_31_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
    ศัพท์
    0.24
    🅴
    0.24
    zicht
    0.24
    ისა
    0.24
    quote
    0.24
     però
    0.23
    arek
    0.23
     Rotating
    0.23
    \|\
    0.23
     OR
    0.22
    POSITIVE LOGITS
    тую
    0.26
     குதிக
    0.24
     комна
    0.22
    िमम
    0.22
    hesi
    0.22
     refractive
    0.22
     disponibil
    0.22
     trophies
    0.22
    chrotron
    0.22
    annabin
    0.22
    Activations Density 0.016%

    No Known Activations