© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157180
    Prev
    Next
    INDEX
    Explanations

    the

    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
    గ
    0.43
    Dw
    0.37
    ayv
    0.36
    ставля
    0.36
    Пра
    0.36
    Ej
    0.35
    Hai
    0.35
    ড্রিম
    0.35
    譙
    0.35
    獪
    0.34
    POSITIVE LOGITS
    chedelic
    0.41
     ـ
    0.41
    oderm
    0.41
     sparked
    0.40
     aired
    0.39
     กรรม
    0.39
    蹈
    0.38
    robat
    0.38
    elands
    0.38
     Foot
    0.37
    Activations Density 0.001%

    No Known Activations