© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133740
    Prev
    Next
    INDEX
    Explanations

    ž, š, ť, í, ů, ň, é, á, é, ě

    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_1_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
    ي
    1.63
    ется
    1.42
    ه
    1.34
    د
    1.25
    জ
    1.20
     μία
    1.12
    э
    1.09
    ยู
    1.03
    ກ
    1.03
    ਹ
    1.01
    POSITIVE LOGITS
    0
    1.16
    of
    1.15
    ru
    1.13
    l
    1.13
    2
    1.05
    line
    1.00
    ist
    0.99
    light
    0.99
    list
    0.98
    p
    0.98
    Activations Density 0.000%

    No Known Activations