© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174395
    Prev
    Next
    INDEX
    Explanations

    resource or reference

    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_20_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
    ೩
    0.42
     mão
    0.41
     விழா
    0.41
    ментов
    0.40
     mundial
    0.40
     கைய
    0.40
     estilos
    0.39
    bil
    0.38
     தினம்
    0.38
    över
    0.38
    POSITIVE LOGITS
    чительно
    0.43
    mmHg
    0.40
    ous
    0.40
     ಸ್ವ
    0.39
    废
    0.39
    ports
    0.39
     absent
    0.39
     RS
    0.38
    December
    0.38
     Meaning
    0.38
    Activations Density 0.002%

    No Known Activations