© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166512
    Prev
    Next
    INDEX
    Explanations

    tried seen medical surgery

    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_34_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
     pernah
    1.38
    เคย
    1.29
     เคย
    1.13
    曾经
    1.09
    曾經
    1.08
    曾
    1.05
    曾在
    1.03
     ooit
    0.92
    有过
    0.90
    看过
    0.85
    POSITIVE LOGITS
     একটু
    0.38
     occurring
    0.37
     Ac
    0.35
     הור
    0.35
    ORDON
    0.35
     finding
    0.34
     Finding
    0.34
     UILabel
    0.34
    ดย
    0.33
    兀
    0.33
    Activations Density 0.019%

    No Known Activations