© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210676
    Prev
    Next
    INDEX
    Explanations

    NY and

    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_5_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
    м
    1.37
    к
    1.31
    م
    1.16
    ம்
    1.12
    क
    1.08
    ک
    1.04
    ant
    1.03
    ன்
    1.02
    ك
    1.00
    ли
    0.98
    POSITIVE LOGITS
     have
    1.16
     has
    1.16
    has
    0.93
    S
    0.89
    '
    0.89
     heeft
    0.89
    有助于
    0.88
    了他
    0.87
    {
    0.87
    Have
    0.86
    Activations Density 0.001%

    No Known Activations