© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24132
    Prev
    Next
    INDEX
    Explanations

    say "interval"

    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
     Dalib
    0.37
    +-
    0.34
    ণী
    0.33
     Leb
    0.33
     Ross
    0.33
     Hospitality
    0.33
     hospitality
    0.33
     Rudolph
    0.33
    窩
    0.33
     cliff
    0.32
    POSITIVE LOGITS
     Inter
    2.47
    inter
    2.45
    Inter
    2.39
     интер
    2.25
     інтер
    2.11
     인터
    2.02
     inter
    1.97
     interv
    1.87
     INTER
    1.84
    INTER
    1.82
    Activations Density 0.021%

    No Known Activations