© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38847
    Prev
    Next
    INDEX
    Explanations

    expect the unexpected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    钀
    0.60
    PLE
    0.58
    ຮູ້
    0.58
    IZZ
    0.57
    DEL
    0.57
    イ
    0.57
    Ol
    0.56
     McA
    0.55
     इसकी
    0.55
    (“
    0.55
    POSITIVE LOGITS
     modernen
    0.55
     fieles
    0.55
     m
    0.53
     immersive
    0.52
     messy
    0.51
     adaptive
    0.50
     pura
    0.50
    systems
    0.50
     worst
    0.48
     volatile
    0.48
    Activations Density 0.028%

    No Known Activations