© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79437
    Prev
    Next
    INDEX
    Explanations

    drew attention or criticism

    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_0_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
    k
    1.30
     dàng
    1.15
    kup
    1.05
     pomeriggio
    1.04
    )。
    1.03
     impresa
    1.03
    "।
    1.02
     οποία
    1.02
    kosten
    1.02
    IN
    1.01
    POSITIVE LOGITS
    ر
    2.13
    ان
    2.00
    ل
    1.99
    л
    1.97
    an
    1.92
    р
    1.92
    ية
    1.84
    й
    1.77
    er
    1.62
    ки
    1.60
    Activations Density 0.000%

    No Known Activations