© 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. 112705
    Prev
    Next
    INDEX
    Explanations

    tajine, tajmaʿ, tan

    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
    า
    1.23
    ين
    1.20
    O
    1.01
    าค
    0.95
    ในช่วง
    0.93
    In
    0.91
    RO
    0.91
    ți
    0.91
     σε
    0.91
     alebo
    0.87
    POSITIVE LOGITS
    s
    1.70
    t
    1.63
     to
    1.33
    sü
    1.32
    \}
    1.28
    r
    1.24
     on
    1.19
    ä
    1.19
     with
    1.17
    m
    1.16
    Activations Density 0.000%

    No Known Activations