© 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. 32617
    Prev
    Next
    INDEX
    Explanations

    Yo

    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
     w
    0.70
     W
    0.49
     huynh
    0.43
     반
    0.43
    w
    0.42
     डी
    0.42
    abang
    0.42
    반
    0.41
     डब्ल्यू
    0.41
    Ｆ
    0.40
    POSITIVE LOGITS
     getTotal
    0.39
    
    0.38
     SPARSE
    0.37
    wertung
    0.36
    শিরোনাম
    0.36
     osmotic
    0.36
    ^{*}}\
    0.36
    onti
    0.35
     gnome
    0.35
     ঘটছে
    0.35
    Activations Density 0.006%

    No Known Activations