© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171527
    Prev
    Next
    INDEX
    Explanations

    genome sequencing and mapping

    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_20_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
    elif
    0.45
    Old
    0.41
    d
    0.40
     wszystkie
    0.38
    King
    0.38
    D
    0.38
    Gif
    0.38
     Championship
    0.37
     ako
    0.37
    viz
    0.37
    POSITIVE LOGITS
     SPARSE
    0.43
    speedboat
    0.42
     పథ
    0.40
    IVERS
    0.39
    ASER
    0.38
    خصة
    0.38
     SLAs
    0.38
     этим
    0.37
     ConcurrentTask
    0.37
    ̖
    0.37
    Activations Density 0.001%

    No Known Activations