© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53393
    Prev
    Next
    INDEX
    Explanations

    say "A" words with accents

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    ्वती
    0.37
    𝒊
    0.37
    𝘶
    0.37
    ᵗ
    0.37
     Wessex
    0.37
    uant
    0.35
    ʳ
    0.35
    𝒈
    0.35
     अध्य
    0.34
    നേ
    0.34
    POSITIVE LOGITS
    Á
    1.20
     Á
    1.14
     الآ
    1.05
     Ã
    1.05
    á
    1.02
     á
    0.97
    å
    0.95
     Ά
    0.94
    آ
    0.94
     Å
    0.93
    Activations Density 0.022%

    No Known Activations