© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234448
    Prev
    Next
    INDEX
    Explanations

    relax consciously, bring, Close, Imagine

    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_32_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
     صدای
    0.42
     आवाज
    0.41
    声音
    0.40
    技术
    0.39
    技術
    0.39
    进
    0.38
     suara
    0.38
    ක්‍
    0.37
     واخ
    0.37
    Voice
    0.37
    POSITIVE LOGITS
    ुरु
    0.40
    的说
    0.40
     abord
    0.37
    袍
    0.37
     goatee
    0.36
     лаь
    0.36
     сутки
    0.35
     Transport
    0.35
     indispens
    0.35
     Mott
    0.35
    Activations Density 0.014%

    No Known Activations