© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148511
    Prev
    Next
    INDEX
    Explanations

    Vu

    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_59_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
    AMT
    0.44
    VM
    0.44
     newVal
    0.43
    AMS
    0.40
    PS
    0.39
    MS
    0.38
    ℙ
    0.38
    ْم
    0.37
    HEIM
    0.37
     Vishal
    0.37
    POSITIVE LOGITS
    rode
    0.46
    ोटी
    0.43
    iladi
    0.43
    adto
    0.41
    elapse
    0.41
     तया
    0.40
    ullah
    0.40
    ㅝ
    0.40
     बनी
    0.39
    ەل
    0.39
    Activations Density 0.000%

    No Known Activations