© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33717
    Prev
    Next
    INDEX
    Explanations

    Ras

    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_50_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
    ದ್
    0.41
    volley
    0.39
    ovor
    0.39
    ப்பூ
    0.37
     बीएड
    0.37
     verbeter
    0.37
    improved
    0.37
    ɽ
    0.37
     improved
    0.36
     reconst
    0.36
    POSITIVE LOGITS
    illas
    0.41
    共通
    0.40
    疳
    0.37
    stå
    0.36
    იკ
    0.36
     WIN
    0.36
     stov
    0.36
    sette
    0.35
    aille
    0.35
    جز
    0.35
    Activations Density 0.001%

    No Known Activations