© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212957
    Prev
    Next
    INDEX
    Explanations

    of

    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_43_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
    鯽
    0.41
     yed
    0.40
    ittee
    0.37
    ittees
    0.37
     Yed
    0.36
     স্বাদ
    0.36
    成立
    0.36
     持
    0.36
     ദ
    0.35
    资格
    0.35
    POSITIVE LOGITS
    Universal
    0.64
     universal
    0.62
     Universal
    0.59
    universal
    0.59
     ইউনিভার
    0.45
     यूनिवर्सल
    0.43
    Global
    0.43
     విధ
    0.42
     универса
    0.41
     univerz
    0.40
    Activations Density 0.001%

    No Known Activations