© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234315
    Prev
    Next
    INDEX
    Explanations

    Cambridge

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     گفته
    0.42
    дений
    0.39
    朖
    0.39
    uchs
    0.38
    bruk
    0.38
     سلسله
    0.38
     گرد
    0.37
    чете
    0.37
     Bourgoin
    0.37
    brug
    0.37
    POSITIVE LOGITS
    ະ
    0.40
    Ｖ
    0.40
    phoneNumber
    0.39
     CBS
    0.38
    javaHome
    0.38
    rophe
    0.37
    Threshold
    0.36
    ayscale
    0.36
     MD
    0.36
     Median
    0.36
    Activations Density 0.000%

    No Known Activations