© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127514
    Prev
    Next
    INDEX
    Explanations

    validation metrics and names

    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_3_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
    u
    0.85
     that
    0.77
     đen
    0.71
     américaine
    0.70
    a
    0.67
    อย่าง
    0.66
    ių
    0.66
    하다
    0.64
    leş
    0.64
     untuk
    0.61
    POSITIVE LOGITS
    Validation
    0.82
     Validation
    0.81
    да
    0.81
     вали
    0.78
    ق
    0.78
    ル
    0.78
    দ
    0.76
     validate
    0.75
    ف
    0.74
     validation
    0.74
    Activations Density 0.001%

    No Known Activations