© 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. 143126
    Prev
    Next
    INDEX
    Explanations

    part + suffix

    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
    n
    2.03
    il
    1.91
    r
    1.80
    o
    1.77
    am
    1.75
    em
    1.72
    g
    1.71
    س
    1.70
    al
    1.66
    j
    1.65
    POSITIVE LOGITS
    dır
    1.51
    ם
    1.43
    ری
    1.38
    ı
    1.34
    רי
    1.33
     یو
    1.30
    کس
    1.28
    لی
    1.23
    ۶
    1.22
    ۸
    1.21
    Activations Density 0.000%

    No Known Activations