© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44586
    Prev
    Next
    INDEX
    Explanations

    illegal torrents and activities

    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_13_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
     but
    0.44
     soup
    0.40
     thinking
    0.39
     upset
    0.39
     desenc
    0.39
    o
    0.39
    an
    0.39
    one
    0.38
     segmentation
    0.38
     completion
    0.38
    POSITIVE LOGITS
     محفوظة
    0.42
     राजवंश
    0.42
    LookAndFeels
    0.41
    踝
    0.40
     نە
    0.40
     ఉ
    0.39
     aparecen
    0.38
    𒌑
    0.38
     ശബ്
    0.38
     मकान
    0.38
    Activations Density 0.176%

    No Known Activations