© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133489
    Prev
    Next
    INDEX
    Explanations

    get the

    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_1_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
    ל
    1.50
    د
    1.26
    v
    1.20
    kort
    1.09
    ُ
    1.09
    Z
    1.08
    К
    1.07
    ůže
    1.05
    า
    1.03
    ung
    1.02
    POSITIVE LOGITS
     as
    1.66
     in
    0.97
    s
    0.92
    ות
    0.89
    да
    0.88
     начинается
    0.87
    에요
    0.85
    이었
    0.84
    젼
    0.81
     aswell
    0.80
    Activations Density 0.000%

    No Known Activations