© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24655
    Prev
    Next
    INDEX
    Explanations

    nine or ninth

    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_10_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
    ారి
    0.96
    THAT
    0.88
    ingen
    0.86
    的
    0.85
    í
    0.84
    ի
    0.82
    ěl
    0.81
    '
    0.80
     Ε
    0.79
    an
    0.78
    POSITIVE LOGITS
    ない
    1.05
    ย
    0.93
    リ
    0.89
    ้น
    0.88
    ف
    0.87
    ンの
    0.84
     nine
    0.80
     ninth
    0.80
     رکھنا
    0.80
     जर
    0.77
    Activations Density 0.052%

    No Known Activations