© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48811
    Prev
    Next
    INDEX
    Explanations

    emojis and 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
     place
    0.34
     statt
    0.34
    勰
    0.34
     দেশ
    0.34
     Toutefois
    0.34
     Multiplication
    0.33
    ળી
    0.33
    engers
    0.33
    ステン
    0.33
    leun
    0.33
    POSITIVE LOGITS
    Therates
    0.46
     Ambris
    0.42
     resuelve
    0.41
    říve
    0.39
     meriye
    0.38
     priming
    0.38
    쏨
    0.37
     resolves
    0.36
     accelerates
    0.36
    ozzi
    0.36
    Activations Density 0.001%

    No Known Activations