© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14393
    Prev
    Next
    INDEX
    Explanations

    Barbados

    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_40_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
    嚥
    0.38
    Bob
    0.38
    枤
    0.37
     surfacing
    0.36
    αλλ
    0.36
     nine
    0.35
     Bob
    0.35
    してい
    0.35
    <0xBF>
    0.35
     cerebral
    0.35
    POSITIVE LOGITS
     embar
    0.39
     നീ
    0.36
     నీ
    0.36
     கட்டிட
    0.36
     Saks
    0.36
     تاني
    0.36
     ഇട
    0.35
    waard
    0.34
     चाइल्ड
    0.34
    Vida
    0.34
    Activations Density 0.002%

    No Known Activations