© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169327
    Prev
    Next
    INDEX
    Explanations

    exceptions and threading

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     fmt
    1.29
     :=
    1.20
    fmt
    1.20
     slice
    1.16
    :=
    1.09
     slices
    1.02
     Slice
    0.99
    ([]
    0.96
    Slice
    0.94
    slice
    0.92
    POSITIVE LOGITS
     قصد
    0.43
    ThreadPool
    0.39
     subclass
    0.38
    粔
    0.38
    EXCEPTION
    0.38
     exception
    0.34
    လိ
    0.34
    '])[
    0.33
    exception
    0.33
     threaded
    0.33
    Activations Density 0.005%

    No Known Activations