© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79451
    Prev
    Next
    INDEX
    Explanations

    bek, pak, ista, sensation

    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_0_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
    al
    1.99
    de
    1.82
    ।
    1.76
    l
    1.55
    d
    1.54
    g
    1.49
    ali
    1.43
    。
    1.38
    تها
    1.38
    n
    1.36
    POSITIVE LOGITS
    一
    1.57
     by
    1.22
    人
    1.21
    ă
    1.21
    "
    1.17
    ન
    1.17
    很
    1.16
    ется
    1.14
    中
    1.14
    用
    1.14
    Activations Density 0.001%

    No Known Activations