© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210170
    Prev
    Next
    INDEX
    Explanations

    Greek, Hungarian, and Portuguese articles

    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_10_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
    Τ
    0.93
    O
    0.91
    Т
    0.83
    ول
    0.82
     emoc
    0.76
    린
    0.76
    ایی
    0.75
    ின
    0.73
     созда
    0.73
    of
    0.71
    POSITIVE LOGITS
    in
    0.84
    wang
    0.79
    ve
    0.77
    ne
    0.74
    li
    0.72
    mp
    0.72
    i
    0.72
    ma
    0.71
    pt
    0.70
    lin
    0.70
    Activations Density 0.000%

    No Known Activations