© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32122
    Prev
    Next
    INDEX
    Explanations

    foreign language 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_7_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
    nis
    0.24
    txt
    0.23
    ४
    0.23
    li
    0.23
    aw
    0.22
    www
    0.22
    tel
    0.22
    iring
    0.21
    til
    0.21
    ened
    0.21
    POSITIVE LOGITS
    ка
    0.28
     riguardo
    0.25
     の
    0.23
    ме
    0.22
     whatnot
    0.21
    জ
    0.21
     pluck
    0.21
    до
    0.20
     того
    0.20
    ات
    0.20
    Activations Density 0.069%

    No Known Activations