© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205099
    Prev
    Next
    INDEX
    Explanations

    spanish question starts

    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_6_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
    ма
    1.02
    ায়
    1.01
    וד
    1.00
    ור
    0.99
    ’।
    0.98
     ร
    0.98
     be
    0.96
    بر
    0.95
    </h3>
    0.93
    </strong>
    0.93
    POSITIVE LOGITS
    ed
    1.09
    т
    0.93
    werte
    0.88
     மற்றும்
    0.86
    eries
    0.84
    stations
    0.84
    ombie
    0.82
     facendo
    0.82
    rine
    0.81
    ,
    0.80
    Activations Density 0.002%

    No Known Activations