© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53452
    Prev
    Next
    INDEX
    Explanations

    say "is"

    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_55_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
     IS
    0.63
     Is
    0.56
     Are
    0.54
    Is
    0.49
     é
    0.48
    Are
    0.47
    Là
    0.45
     İs
    0.44
    閤
    0.44
    IsEnabled
    0.43
    POSITIVE LOGITS
    ொருள்
    0.45
     современном
    0.42
    водит
    0.39
    objectManager
    0.39
     एग्जांपल
    0.38
    soup
    0.38
     Slight
    0.38
     Phrase
    0.37
    लाइज
    0.37
     Himmel
    0.37
    Activations Density 0.007%

    No Known Activations