© 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. 79632
    Prev
    Next
    INDEX
    Explanations

    code structure or declarations

    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
    その他の
    0.38
    丰
    0.38
    抜け
    0.38
     diğer
    0.37
     Tong
    0.36
    其他
    0.35
     E
    0.34
     Hard
    0.34
     Claw
    0.34
     éves
    0.34
    POSITIVE LOGITS
    ण्डे
    0.39
    ორის
    0.39
     Сколько
    0.38
     waited
    0.38
    $.\\
    0.38
    otope
    0.38
     wait
    0.37
     “.
    0.36
    CTURE
    0.35
     "_"
    0.35
    Activations Density 0.004%

    No Known Activations