© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32873
    Prev
    Next
    INDEX
    Explanations

    development status

    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_31_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
    认证
    0.38
     zert
    0.33
     tasmim
    0.30
     ermög
    0.30
     запре
    0.28
    iliği
    0.28
     організації
    0.28
     架
    0.28
    cookbook
    0.28
     αντα
    0.27
    POSITIVE LOGITS
     Dev
    0.32
     steadily
    0.31
     critically
    0.31
     continually
    0.30
     Etihad
    0.29
     строительства
    0.29
     priority
    0.29
     comparison
    0.28
     Black
    0.28
     constantly
    0.28
    Activations Density 0.022%

    No Known Activations