© 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. 79291
    Prev
    Next
    INDEX
    Explanations

    case followed by 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
     teg
    0.39
    ༣
    0.36
     روح
    0.36
    Cotton
    0.35
     targ
    0.35
     vorg
    0.35
    mvc
    0.35
     antih
    0.35
     نا
    0.34
    improve
    0.34
    POSITIVE LOGITS
    slate
    0.38
    如果我们
    0.37
     (=
    0.36
    obos
    0.33
     إذا
    0.33
     салы
    0.33
     nếu
    0.32
     whereas
    0.32
    strom
    0.31
    ulam
    0.31
    Activations Density 0.003%

    No Known Activations