© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150920
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ඔබේ
    0.46
     반갑습니다
    0.45
    odimensional
    0.42
    여러분
    0.41
    ışı
    0.40
     itulah
    0.40
     டாக்டர்
    0.40
    ᴿ
    0.39
     අවශ්‍ය
    0.39
    ᱶ
    0.38
    POSITIVE LOGITS
     показатели
    0.42
    ிட்ட
    0.42
    UEFA
    0.42
    FieldSet
    0.41
    Bsky
    0.41
    attuale
    0.40
    Exper
    0.40
    вля
    0.39
    PROCESSING
    0.39
     ciel
    0.38
    Activations Density 0.000%

    No Known Activations