© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163549
    Prev
    Next
    INDEX
    Explanations

    code syntax start

    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_31_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
    营
    0.42
    營
    0.41
    䏌
    0.40
     кў
    0.39
     മാസ
    0.37
     정신
    0.36
    显得
    0.36
     Ki
    0.36
     panor
    0.35
    络
    0.35
    POSITIVE LOGITS
     borrowings
    0.43
     holdings
    0.42
     request
    0.39
     allocation
    0.39
     लोकतंत्र
    0.38
    length
    0.37
    request
    0.37
    boundary
    0.37
     삽니다
    0.37
    召
    0.37
    Activations Density 0.003%

    No Known Activations