© 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. 34307
    Prev
    Next
    INDEX
    Explanations

    name prefixes

    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
     wojewód
    0.38
    Obes
    0.38
     Winchester
    0.37
     fert
    0.37
     الو
    0.37
    ')])
    0.37
     جا
    0.37
    }$.)
    0.37
    ძლ
    0.37
    낮
    0.36
    POSITIVE LOGITS
    ab
    0.43
    mus
    0.42
     aqu
    0.41
     ප්‍රති
    0.40
     aqua
    0.40
    AGON
    0.40
     رق
    0.40
    hora
    0.39
    omus
    0.39
     противо
    0.39
    Activations Density 0.000%

    No Known Activations