© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 103090
    Prev
    Next
    INDEX
    Explanations

    alpine linux variants

    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_16_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
    HasFieldError
    0.52
    교
    0.50
     ఏర్
    0.50
    汅
    0.49
    ሟ
    0.49
    meras
    0.48
    喤
    0.47
    flowing
    0.46
    annels
    0.46
     مو
    0.46
    POSITIVE LOGITS
     I
    0.56
    us
    0.56
     Create
    0.55
    is
    0.50
     you
    0.50
     suite
    0.49
     Party
    0.47
    ão
    0.47
     thief
    0.47
     are
    0.47
    Activations Density 0.000%

    No Known Activations