© 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. 158449
    Prev
    Next
    INDEX
    Explanations

    composition

    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
     кра
    0.38
     vodka
    0.38
     insanity
    0.37
    قر
    0.36
    غال
    0.36
     ፓ
    0.36
     জর
    0.35
    概率
    0.35
    вості
    0.35
    曼
    0.35
    POSITIVE LOGITS
    compos
    0.66
     compos
    0.65
     S
    0.55
     Compos
    0.51
    composite
    0.49
     sav
    0.46
    Composite
    0.46
    S
    0.44
     Among
    0.43
    compose
    0.42
    Activations Density 0.001%

    No Known Activations