© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 131040
    Prev
    Next
    INDEX
    Explanations

    mentioning permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     ：
    0.43
     Examples
    0.40
     Excited
    0.39
     Includes
    0.38
     pressione
    0.38
     INCLUDE
    0.38
     Include
    0.38
     eksempel
    0.38
    经费
    0.38
    汥
    0.38
    POSITIVE LOGITS
     countless
    0.44
    calculated
    0.39
     baked
    0.38
     attainable
    0.37
    ্যাশ
    0.37
     compose
    0.36
    shrink
    0.36
     calculated
    0.35
     mediate
    0.35
     collapses
    0.35
    Activations Density 0.002%

    No Known Activations