© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58807
    Prev
    Next
    INDEX
    Explanations

    seventh

    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_59_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
     eight
    1.02
    八
    0.93
     Eight
    0.91
    eight
    0.89
     आठ
    0.89
     acht
    0.88
    Eight
    0.84
     вось
    0.83
     восем
    0.81
     八
    0.81
    POSITIVE LOGITS
    ৭০
    0.54
     ৭০
    0.50
    Seventh
    0.47
    seventh
    0.47
     seventh
    0.46
     Seventh
    0.46
     七
    0.45
     seventy
    0.44
     sevent
    0.42
    mprj
    0.42
    Activations Density 0.001%

    No Known Activations