© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214955
    Prev
    Next
    INDEX
    Explanations

    occ acc cer

    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_50_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
    Moles
    0.45
    گي
    0.41
    ogi
    0.40
    ева
    0.39
    vanja
    0.39
     读取
    0.38
     బె
    0.38
     ఒ
    0.38
    Gui
    0.38
    ギ
    0.38
    POSITIVE LOGITS
    CC
    0.65
    cc
    0.61
    OCC
    0.61
     cer
    0.59
    occ
    0.59
     cc
    0.57
    커
    0.55
    ocer
    0.54
    acc
    0.53
     CC
    0.53
    Activations Density 0.014%

    No Known Activations