© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198040
    Prev
    Next
    INDEX
    Explanations

    algal toxins

    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_15_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
     חיי
    0.55
     الواي
    0.52
    COMPILE
    0.52
     enjeux
    0.51
     SELF
    0.50
    ಿಕ್
    0.49
     perspectiva
    0.49
    럏
    0.49
    কলাপ
    0.49
     belge
    0.48
    POSITIVE LOGITS
    5
    0.57
     (
    0.54
     =
    0.53
     /
    0.52
    1
    0.52
    M
    0.52
     ,
    0.50
    2
    0.49
    М
    0.48
     "
    0.47
    Activations Density 0.000%

    No Known Activations