© 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. 160991
    Prev
    Next
    INDEX
    Explanations

    Vons, Vondelpark, Vohibasia, Vonage

    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
    i
    1.14
             
    1.09
    l
    1.09
    y
    0.98
     legitim
    0.96
     (
    0.95
    am
    0.93
    r
    0.92
    f
    0.92
    b
    0.91
    POSITIVE LOGITS
    ری
    1.42
    ため
    1.32
    щая
    1.21
    ین
    1.19
    وی
    1.10
    くる
    1.10
    ków
    1.09
    ла
    1.07
    ために
    1.06
    ва
    1.05
    Activations Density 0.000%

    No Known Activations