© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 86685
    Prev
    Next
    INDEX
    Explanations

    closed for times

    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_23_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
    Casino
    0.45
    rins
    0.42
    clin
    0.41
    reaching
    0.40
    ץ
    0.40
    Especially
    0.39
    iculaire
    0.39
    curs
    0.38
    Cock
    0.38
     Casino
    0.38
    POSITIVE LOGITS
     fiat
    0.41
     합동
    0.39
     इलेक्ट्रॉन
    0.38
     Kef
    0.37
     समान
    0.37
     ivy
    0.37
     fur
    0.37
     vinyl
    0.37
     ड
    0.36
     Sahel
    0.35
    Activations Density 0.003%

    No Known Activations