© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121305
    Prev
    Next
    INDEX
    Explanations

    IEEE 754 standard

    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
    Dire
    0.46
    Dir
    0.46
     Dir
    0.45
    暖
    0.44
     Dire
    0.43
    木
    0.39
     accord
    0.38
     Amber
    0.38
    阳光
    0.38
    dire
    0.38
    POSITIVE LOGITS
    apl
    0.46
    홉
    0.43
     arriver
    0.40
    ngth
    0.39
     footballer
    0.38
    asc
    0.37
    arriv
    0.37
     retriever
    0.37
     arrib
    0.37
     envy
    0.36
    Activations Density 0.001%

    No Known Activations