© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51599
    Prev
    Next
    INDEX
    Explanations

    shallow depth of field

    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_10_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
    up
    0.51
    يد
    0.46
    uate
    0.46
    tipo
    0.46
     Среди
    0.45
    spaced
    0.45
    띤
    0.45
     Он
    0.45
    spel
    0.44
    post
    0.44
    POSITIVE LOGITS
     Deep
    0.93
     profond
    0.91
     sâu
    0.89
    Deep
    0.86
    深度
    0.85
     depths
    0.83
     profundo
    0.83
     profonde
    0.82
     profondeur
    0.82
     deep
    0.82
    Activations Density 0.017%

    No Known Activations