© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205708
    Prev
    Next
    INDEX
    Explanations

    end punctuation or code markers

    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_25_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
     Classe
    0.43
     Response
    0.43
     Salmon
    0.42
     F
    0.41
     Tired
    0.41
     Dred
    0.41
     Alpine
    0.39
     Listed
    0.39
     Wa
    0.39
     Batter
    0.39
    POSITIVE LOGITS
    )")
    0.40
    stays
    0.40
     коне
    0.39
    过程中
    0.38
    觛
    0.38
    我还
    0.37
    sbParams
    0.37
    ;")
    0.37
    Buenos
    0.36
    >")
    0.36
    Activations Density 0.001%

    No Known Activations