© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108787
    Prev
    Next
    INDEX
    Explanations

    manslaughter or words ending in ance

    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_2_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
    大
    0.98
    માં
    0.92
    nes
    0.90
    itt
    0.88
    ای
    0.86
    いき
    0.84
    ney
    0.82
    ete
    0.82
    riculum
    0.79
    man
    0.79
    POSITIVE LOGITS
    ר
    1.29
    (
    1.26
     I
    1.19
    1.09
     M
    0.98
    a
    0.96
     L
    0.95
     K
    0.95
     A
    0.94
     U
    0.92
    Activations Density 0.001%

    No Known Activations