© 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. 136190
    Prev
    Next
    INDEX
    Explanations

    possess and hold

    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
    на
    0.61
    ത്തില
    0.60
    as
    0.59
     quedan
    0.59
     निकालकर
    0.59
    ко
    0.59
     adecuadas
    0.58
    كما
    0.57
    秦
    0.57
    не
    0.57
    POSITIVE LOGITS
    ’
    0.89
     alloys
    0.57
    vais
    0.57
     flaws
    0.57
     atherosclerosis
    0.56
     shortcomings
    0.56
    årt
    0.55
    ‌است
    0.55
    ศ์
    0.55
    omsday
    0.54
    Activations Density 0.003%

    No Known Activations