© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123031
    Prev
    Next
    INDEX
    Explanations

    number or list item prefixes

    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_37_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
    리어
    0.42
     interrupts
    0.37
    icular
    0.37
     hitherto
    0.37
     impe
    0.36
    once
    0.36
     competency
    0.36
    椹
    0.36
     SFR
    0.36
     interrupt
    0.35
    POSITIVE LOGITS
     Bangalore
    0.39
     goomba
    0.37
    Lov
    0.36
     बेंगल
    0.36
     गाइ
    0.36
     दुष्प्रभाव
    0.36
     Lov
    0.35
    DataManager
    0.35
     ਸੀ
    0.35
    ราง
    0.35
    Activations Density 0.000%

    No Known Activations