© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177958
    Prev
    Next
    INDEX
    Explanations

    purpose or specific conditions

    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_24_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
    ورس
    0.41
    мость
    0.39
     Option
    0.38
     brackets
    0.37
     LINES
    0.37
     Ohm
    0.36
    хим
    0.36
    鹜
    0.36
     бюджет
    0.36
     delimited
    0.36
    POSITIVE LOGITS
     laissent
    0.42
     કંઈ
    0.41
     récup
    0.39
     peuvent
    0.38
    শিল্পী
    0.38
     repub
    0.38
     convi
    0.38
    आगे
    0.37
    ily
    0.37
     Norwood
    0.36
    Activations Density 0.000%

    No Known Activations