© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87034
    Prev
    Next
    INDEX
    Explanations

    Ryzen CPUs

    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_3_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
    াইব
    0.63
    Evening
    0.61
    𝙝
    0.60
    Christian
    0.59
    Tub
    0.57
    𝙧
    0.56
    D
    0.56
    Rig
    0.55
    Cong
    0.54
    Sound
    0.54
    POSITIVE LOGITS
    ر
    0.82
    ла
    0.75
    े
    0.73
    ся
    0.72
    tra
    0.71
    да
    0.71
    다
    0.70
     is
    0.69
    tter
    0.68
    。
    0.68
    Activations Density 0.001%

    No Known Activations