© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142519
    Prev
    Next
    INDEX
    Explanations

    lignocellulose, omycetes

    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_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <
    0.55
    Luck
    0.54
     Heads
    0.52
     Luck
    0.49
    юсь
    0.49
    लिसिस
    0.48
     SAFE
    0.48
    空格
    0.47
     Stability
    0.47
    Buddy
    0.46
    POSITIVE LOGITS
     пан
    0.54
    </b>
    0.53
    financed
    0.53
    ችን
    0.52
     fanciful
    0.52
    كما
    0.52
    funded
    0.52
    editar
    0.52
    м
    0.52
     appealed
    0.51
    Activations Density 0.000%

    No Known Activations