© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65096
    Prev
    Next
    INDEX
    Explanations

    approximate

    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_46_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
     liik
    0.40
    려
    0.38
     Mär
    0.38
     average
    0.38
    റിൽ
    0.38
     औसत
    0.38
     أنّ
    0.38
    astar
    0.37
    केजी
    0.37
    kola
    0.36
    POSITIVE LOGITS
    utable
    0.40
    MENTS
    0.38
     несу
    0.37
    ☚
    0.37
    ured
    0.36
    ቪ
    0.35
    менти
    0.35
    ೇಶ
    0.34
    ments
    0.34
     поня
    0.34
    Activations Density 0.004%

    No Known Activations