© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250416
    Prev
    Next
    INDEX
    Explanations

    Dw

    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_56_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
    arma
    0.38
    ях
    0.37
    또한
    0.36
    yx
    0.35
    υχ
    0.35
    acia
    0.35
    `)
    0.35
    िरी
    0.34
     usp
    0.34
    iatica
    0.34
    POSITIVE LOGITS
     Cumm
    0.39
    HeightSizeMode
    0.39
    さら
    0.38
     дальней
    0.37
     हेयर
    0.36
    ی
    0.36
    +](
    0.36
     Calyce
    0.35
     comenzamos
    0.35
    ilium
    0.34
    Activations Density 0.000%

    No Known Activations