© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229172
    Prev
    Next
    INDEX
    Explanations

    URLs

    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_57_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
    Ｊ
    0.45
     o
    0.43
     ObjData
    0.41
    JPanel
    0.41
     pcMove
    0.40
     о
    0.38
     ο
    0.38
    J
    0.38
    вую
    0.37
    চ্ছ
    0.37
    POSITIVE LOGITS
     Loves
    0.40
     defy
    0.39
    ushal
    0.39
     recognising
    0.39
     v
    0.38
     L
    0.38
     enables
    0.38
     Neither
    0.37
     equalities
    0.37
     Gets
    0.36
    Activations Density 0.000%

    No Known Activations