© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205685
    Prev
    Next
    INDEX
    Explanations

    parts of systems/organizations

    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
    的发展
    0.58
    的高
    0.55
    的山
    0.51
    のア
    0.50
    的大
    0.50
    的长
    0.49
    的海
    0.48
    旳
    0.47
    的使用
    0.47
    的不
    0.45
    POSITIVE LOGITS
    બે
    0.40
     частью
    0.40
     부분이
    0.38
    вшего
    0.37
     ;,
    0.37
     부분
    0.37
    遺
    0.37
     모습을
    0.36
    дового
    0.35
     부분을
    0.35
    Activations Density 0.006%

    No Known Activations