© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221942
    Prev
    Next
    INDEX
    Explanations

    languages and operations

    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
    ad
    0.55
    w
    0.52
     immune
    0.48
    (
    0.48
     Poste
    0.47
    v
    0.47
    uldig
    0.46
    ھا
    0.45
     ALLE
    0.45
    (",")
    0.45
    POSITIVE LOGITS
     сооб
    0.55
    Ⴊ
    0.52
     decidido
    0.50
    と呼ばれる
    0.50
    𝒂
    0.48
     Среди
    0.47
    粮
    0.47
    ική
    0.47
     condivid
    0.47
     คิด
    0.46
    Activations Density 0.000%

    No Known Activations