© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24504
    Prev
    Next
    INDEX
    Explanations

    Prometheus and Atlas

    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
    og
    1.01
    ip
    0.99
    -
    0.96
    at
    0.95
    ra
    0.92
    em
    0.91
    ur
    0.91
    er
    0.88
    ar
    0.88
    us
    0.85
    POSITIVE LOGITS
     Até
    0.88
     fue
    0.81
     LA
    0.80
     UB
    0.78
     UNA
    0.78
     sería
    0.77
     UN
    0.77
     UNE
    0.77
     ATLAS
    0.75
     UP
    0.74
    Activations Density 0.014%

    No Known Activations