© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102200
    Prev
    Next
    INDEX
    Explanations

    fire wall

    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_16_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
    牘
    0.53
    ristown
    0.52
    化物
    0.50
     土
    0.49
     às
    0.49
     বিশাল
    0.49
    viation
    0.48
    âce
    0.48
    Arena
    0.48
     vám
    0.47
    POSITIVE LOGITS
    لق
    0.47
     It
    0.47
    ለ
    0.46
     Μα
    0.45
     conduit
    0.44
     offenders
    0.43
    ті
    0.43
     believe
    0.42
     impedir
    0.42
     Fonseca
    0.42
    Activations Density 0.000%

    No Known Activations