© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60334
    Prev
    Next
    INDEX
    Explanations

    learn or clean

    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_2_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
    f
    1.45
    wiches
    1.26
    fär
    1.26
    פ
    1.21
    1.20
    is
    1.18
     powied
    1.18
    ー
    1.16
    Item
    1.15
    ること
    1.09
    POSITIVE LOGITS
    ки
    1.07
     compartments
    1.07
     landmarks
    1.03
    يا
    1.00
     workplaces
    1.00
    ب
    0.98
    ням
    0.97
    ня
    0.96
     constituencies
    0.95
     appointments
    0.93
    Activations Density 0.000%

    No Known Activations