© 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. 158654
    Prev
    Next
    INDEX
    Explanations

    AI and knowledge

    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
     ध्व
    0.38
    ريخ
    0.38
     Rainbow
    0.37
    ന്നു
    0.37
     Gothic
    0.37
    Rainbow
    0.37
    ｳ
    0.37
    ायर
    0.37
    mie
    0.37
     Inoue
    0.37
    POSITIVE LOGITS
    kel
    0.45
    ikel
    0.44
    rud
    0.44
    클
    0.43
    KEL
    0.42
    licht
    0.41
     Kum
    0.41
     Clint
    0.40
    คล
    0.39
    ikli
    0.39
    Activations Density 0.012%

    No Known Activations