© 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. 50926
    Prev
    Next
    INDEX
    Explanations

    breaking long lines

    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
    inae
    0.43
     canal
    0.38
    句
    0.38
     yalnız
    0.37
     सनी
    0.37
     vacancy
    0.36
     анализ
    0.36
    remove
    0.35
     Canal
    0.35
    OCKS
    0.35
    POSITIVE LOGITS
     long
    0.43
     mult
    0.43
    长
    0.42
     multist
    0.40
     langen
    0.40
     multip
    0.39
     multi
    0.39
    Multi
    0.39
     Panjang
    0.39
     longer
    0.38
    Activations Density 0.006%

    No Known Activations