© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125791
    Prev
    Next
    INDEX
    Explanations

    call to action

    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_37_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
     Short
    0.45
     short
    0.43
     asking
    0.42
    Short
    0.40
    short
    0.40
     शॉर्ट
    0.39
     крат
    0.39
    旦
    0.39
    SHORT
    0.38
     ट्वीट
    0.38
    POSITIVE LOGITS
     Interested
    0.50
    Interested
    0.44
    สนใจ
    0.40
    ありがとうございました
    0.40
     interested
    0.39
     wasteful
    0.39
     Munn
    0.39
     想
    0.39
    いません
    0.38
     Prospective
    0.38
    Activations Density 0.001%

    No Known Activations