© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9029
    Prev
    Next
    INDEX
    Explanations

    sincerely,

    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_40_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
     Cover
    0.38
     cover
    0.36
     कवर
    0.35
    cover
    0.35
    Cover
    0.33
     letter
    0.32
    ｜
    0.31
     Letter
    0.30
    letter
    0.29
    Letter
    0.29
    POSITIVE LOGITS
    St
    0.37
    En
    0.32
     En
    0.29
    𝐶
    0.28
    '></
    0.28
    جب
    0.28
    㗽
    0.27
     توصیه
    0.27
     St
    0.27
     Sag
    0.27
    Activations Density 0.010%

    No Known Activations