© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165873
    Prev
    Next
    INDEX
    Explanations

    theory with application

    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_34_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
    搬型
    0.38
     university
    0.36
    অধ
    0.36
     complexes
    0.35
     دانشگاه
    0.34
    稆
    0.34
     빙
    0.34
     حاصل
    0.34
     attainment
    0.34
    損傷
    0.34
    POSITIVE LOGITS
    idea
    0.45
    铺
    0.42
    quant
    0.42
    態度
    0.40
     idea
    0.40
    鋪
    0.40
    الغ
    0.38
    appara
    0.38
     이론
    0.38
     theoret
    0.38
    Activations Density 0.007%

    No Known Activations