© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27636
    Prev
    Next
    INDEX
    Explanations

    bucks, redeem, MBUX

    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_10_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
    (
    1.03
    ს
    0.84
    નું
    0.80
    ב
    0.79
    s
    0.78
    ক
    0.78
    ک
    0.75
     opaque
    0.70
     imperme
    0.69
    igueur
    0.69
    POSITIVE LOGITS
    8
    0.63
    oc
    0.62
    three
    0.60
    0
    0.59
     چ
    0.59
    dog
    0.57
    ０
    0.57
     كرة
    0.56
    dem
    0.56
    textvariable
    0.55
    Activations Density 0.000%

    No Known Activations