© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42010
    Prev
    Next
    INDEX
    Explanations

    character encodings

    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_22_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
    PlayerSelector
    0.43
    स्तेमाल
    0.42
    㢼
    0.41
     मोटे
    0.40
    फारिश
    0.40
     cláus
    0.40
    ग्रीकल्चर
    0.39
    を使って
    0.39
     Atletico
    0.39
    ഞ്ഞെടു
    0.39
    POSITIVE LOGITS
     প্রকাশ
    0.42
    idden
    0.41
    publish
    0.40
     ه
    0.40
     மூ
    0.39
     вий
    0.39
     الخبر
    0.39
    profil
    0.38
     గుర్
    0.38
    ారులు
    0.38
    Activations Density 0.000%

    No Known Activations