© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6692
    Prev
    Next
    INDEX
    Explanations

    color, url, language codes

    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_40_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
    牘
    0.39
     Committee
    0.37
     contactless
    0.37
     committee
    0.35
    начально
    0.34
     regulated
    0.34
    Committee
    0.34
    fft
    0.34
     record
    0.33
    noindent
    0.33
    POSITIVE LOGITS
    parametric
    0.38
    סה
    0.38
    PARAM
    0.37
     eTo
    0.36
     mish
    0.35
    퓨
    0.35
     refres
    0.35
     божомол
    0.35
    verture
    0.35
    囘
    0.35
    Activations Density 0.021%

    No Known Activations