© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123678
    Prev
    Next
    INDEX
    Explanations

    class-based

    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_3_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
    r
    0.72
    ac
    0.68
    k
    0.66
    ou
    0.63
    ാണ
    0.63
    yr
    0.63
    ل
    0.63
    l
    0.61
    im
    0.61
    us
    0.61
    POSITIVE LOGITS
    Class
    0.66
    class
    0.63
    ckte
    0.61
    스는
    0.61
    className
    0.59
    アイテム
    0.58
    스의
    0.58
    UID
    0.57
    ˒
    0.57
    ния
    0.55
    Activations Density 0.001%

    No Known Activations