© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3502
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers or suffixes

    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_39_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
    സ്റ്റി
    0.38
    ᓗ
    0.38
     ಹೆಚ್ಚಿನ
    0.36
    هل
    0.36
     Gaming
    0.36
    oling
    0.36
     Sixteen
    0.36
    Secondly
    0.36
    стного
    0.36
    enial
    0.35
    POSITIVE LOGITS
    第
    0.75
     第
    0.59
     nth
    0.50
     nº
    0.39
     thứ
    0.38
     sebesar
    0.38
    วันที่
    0.38
    ^{-(
    0.37
     Rodgers
    0.37
    ведении
    0.36
    Activations Density 0.388%

    No Known Activations