© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158037
    Prev
    Next
    INDEX
    Explanations

    shekel

    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_2_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
    s
    2.33
    i
    1.73
    d
    1.66
    t
    1.64
    y
    1.55
    ts
    1.39
    se
    1.38
    il
    1.36
    ru
    1.30
    r
    1.25
    POSITIVE LOGITS
    ية
    1.64
    ки
    1.51
    の話
    1.44
    и
    1.38
    ى
    1.34
    は
    1.24
    ৬
    1.24
    е
    1.19
    ານ
    1.16
    あります
    1.15
    Activations Density 0.000%

    No Known Activations