© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11526
    Prev
    Next
    INDEX
    Explanations

    assembly code and programming phrases

    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_40_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
    ส่
    0.39
    umbr
    0.37
    㫴
    0.37
     మొ
    0.36
    టం
    0.36
    itando
    0.36
    ల్లి
    0.36
    唸
    0.35
    uffle
    0.34
    再
    0.34
    POSITIVE LOGITS
     tī
    0.40
     logical
    0.40
     Ό
    0.39
     Multip
    0.38
    multip
    0.38
    𝘈
    0.38
    𝗔
    0.37
    ベース
    0.37
     Logical
    0.37
     LY
    0.36
    Activations Density 0.010%

    No Known Activations