© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36102
    Prev
    Next
    INDEX
    Explanations

    combining information and reasoning

    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
    ப்பத
    0.31
     dipping
    0.30
     पिछड़ा
    0.29
     pyramid
    0.28
     Mapping
    0.28
     mio
    0.28
    INED
    0.28
    <start_of_image>
    0.27
    悹
    0.27
     mapping
    0.27
    POSITIVE LOGITS
     ஆம்
    0.34
     verstehen
    0.31
    cook
    0.31
     gebruiken
    0.31
     সর্বোচ্চ
    0.31
     استخدم
    0.30
     сюда
    0.30
    ޖ
    0.30
     እንዳ
    0.30
    伎
    0.30
    Activations Density 0.009%

    No Known Activations