© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158091
    Prev
    Next
    INDEX
    Explanations

    Ag or GI

    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
     to
    2.19
    t
    1.60
    та
    1.53
    u
    1.52
    z
    1.45
    я
    1.45
    ル
    1.43
    ных
    1.42
    マ
    1.42
    л
    1.41
    POSITIVE LOGITS
    (
    1.19
     I
    0.95
    सँग
    0.87
    ти
    0.80
    =>{
    0.79
    є
    0.78
     Handels
    0.78
     Kein
    0.75
    ara
    0.74
     Bestellung
    0.74
    Activations Density 0.000%

    No Known Activations