© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250751
    Prev
    Next
    INDEX
    Explanations

    sections or numbers

    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_56_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
    Ὅ
    0.40
    стой
    0.40
     【
    0.38
    ]'
    0.38
    تماد
    0.37
    Qué
    0.37
     jogs
    0.36
    ขับ
    0.36
    ёма
    0.36
    ],"
    0.35
    POSITIVE LOGITS
    Elemental
    0.39
     Elemental
    0.38
     threefold
    0.36
     பக்க
    0.36
     lu
    0.35
     elemental
    0.35
     பக்கம்
    0.35
     connection
    0.34
    င်း
    0.34
     logic
    0.34
    Activations Density 0.000%

    No Known Activations