© 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. 37709
    Prev
    Next
    INDEX
    Explanations

    side hustle

    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
    ים
    1.05
    ی
    0.97
    ের
    0.80
    ों
    0.79
    ни
    0.77
    0
    0.74
    ς
    0.71
    1
    0.69
    s
    0.66
    ط
    0.61
    POSITIVE LOGITS
    C
    1.09
    S
    1.09
    B
    1.08
    F
    0.98
    T
    0.97
    R
    0.90
    M
    0.89
    D
    0.88
    P
    0.86
    K
    0.85
    Activations Density 0.001%

    No Known Activations