© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7545
    Prev
    Next
    INDEX
    Explanations

    eight in multiple languages

    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_40_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
    etha
    0.32
    Alf
    0.29
     bant
    0.29
     Forms
    0.27
     فائ
    0.27
    沆
    0.27
    วาง
    0.26
    angwa
    0.26
    atering
    0.26
     Bant
    0.26
    POSITIVE LOGITS
     eight
    0.47
    八
    0.45
    Eight
    0.44
     八
    0.44
    eight
    0.43
     восем
    0.42
     huit
    0.41
     acht
    0.39
     Eight
    0.38
     oito
    0.38
    Activations Density 0.032%

    No Known Activations