© 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. 25725
    Prev
    Next
    INDEX
    Explanations

    'at' followed by numbers

    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
    ל
    0.79
    ل
    0.77
    बाल
    0.73
    USTR
    0.73
    OS
    0.68
    E
    0.68
    Сан
    0.68
    Samb
    0.67
    Os
    0.66
     После
    0.66
    POSITIVE LOGITS
    er
    0.73
    o
    0.70
     nº
    0.68
     infestations
    0.67
    est
    0.66
    ρός
    0.66
     noteworthy
    0.62
     orchards
    0.62
     centric
    0.61
     cuttings
    0.60
    Activations Density 0.000%

    No Known Activations