© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21797
    Prev
    Next
    INDEX
    Explanations

    span

    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_56_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
    stencil
    0.38
    нього
    0.38
     કેટલી
    0.37
    潅
    0.37
    राम
    0.36
    جا
    0.36
     stencil
    0.35
    )}=
    0.35
    ើន
    0.35
     lai
    0.35
    POSITIVE LOGITS
     span
    1.70
     Span
    1.42
    span
    1.29
    Span
    1.29
     spans
    1.05
    SPAN
    1.05
     spanned
    0.91
     spanning
    0.83
     chord
    0.72
     Spann
    0.59
    Activations Density 0.032%

    No Known Activations