© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87868
    Prev
    Next
    INDEX
    Explanations

    wool, wright, crook

    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_3_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
    IA
    0.72
    AM
    0.62
    ام
    0.61
     Bioinformatics
    0.61
     (
    0.61
    W
    0.61
    T
    0.59
     [(
    0.58
    ر
    0.57
    V
    0.57
    POSITIVE LOGITS
     étend
    0.70
     എന്നാൽ
    0.69
     estándares
    0.69
     criticize
    0.68
    ))$
    0.67
     can
    0.67
    τει
    0.67
    ла
    0.66
     malades
    0.66
    付ける
    0.66
    Activations Density 0.001%

    No Known Activations