© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121776
    Prev
    Next
    INDEX
    Explanations

    Orion, Ornitho, Oco, Oriani

    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_3_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
    osterone
    0.63
    Mun
    0.61
    Iceland
    0.61
     Portsmouth
    0.59
    Ê
    0.59
    Evans
    0.58
    ULTURE
    0.58
    <0xD0>
    0.57
     European
    0.57
     December
    0.57
    POSITIVE LOGITS
    .
    0.79
    ।
    0.74
    ات
    0.71
    ról
    0.70
    iado
    0.65
    eer
    0.64
    ről
    0.64
    iqués
    0.63
    ().
    0.62
    adığı
    0.62
    Activations Density 0.000%

    No Known Activations