© 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. 161233
    Prev
    Next
    INDEX
    Explanations

    Chinese, Japanese, Hebrew, Greek, Arabic, Bengali, Russian, Czech, Slovak, English names

    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
    a
    1.50
    j
    1.43
    ิ
    1.32
    l
    1.29
    н
    1.27
    ه
    1.27
    T
    1.24
    an
    1.19
    ah
    1.18
    n
    1.17
    POSITIVE LOGITS
    一大
    1.06
    ة
    0.99
    ため
    0.97
    莱
    0.95
     Ελλά
    0.89
     असं
    0.86
     Gunners
    0.86
    ার
    0.85
    блі
    0.84
    ský
    0.84
    Activations Density 0.000%

    No Known Activations