© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25558
    Prev
    Next
    INDEX
    Explanations

    lazy dog

    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_10_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
    ρι
    0.65
    ်
    0.64
    vál
    0.61
     jamás
    0.59
     ايجاد
    0.58
    ou
    0.57
    ர்
    0.57
     ô
    0.57
     Inglaterra
    0.56
    يد
    0.56
    POSITIVE LOGITS
     I
    0.63
     Ook
    0.62
     assembl
    0.61
     публі
    0.61
     this
    0.60
     վ
    0.60
    ↵
    0.60
     are
    0.58
     the
    0.57
     medit
    0.57
    Activations Density 0.001%

    No Known Activations