© 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. 4249
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Women
    0.41
    ồn
    0.39
    bilical
    0.38
    駝
    0.38
     Women
    0.38
    contiguous
    0.38
     cabang
    0.37
     المرأة
    0.36
    仰
    0.36
     داره
    0.36
    POSITIVE LOGITS
    fieldType
    0.43
    ேன்
    0.41
     stycznia
    0.41
    Ⴉ
    0.39
    단을
    0.39
     चिन्ह
    0.39
     অতঃ
    0.39
    ínas
    0.38
     Khr
    0.38
    REME
    0.38
    Activations Density 0.000%

    No Known Activations