© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45120
    Prev
    Next
    INDEX
    Explanations

    flatness, lack of excitement

    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_13_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
     Sword
    0.59
     Law
    0.57
    约为
    0.53
    www
    0.52
    <0x89>
    0.51
    řej
    0.50
     Dealers
    0.50
    р
    0.50
     Birla
    0.50
     Wheeler
    0.50
    POSITIVE LOGITS
     skit
    0.63
     rations
    0.61
     darts
    0.57
     cannabinoids
    0.56
     voud
    0.55
     drains
    0.54
     갑
    0.54
     capillaries
    0.54
     hydrates
    0.54
     били
    0.54
    Activations Density 0.002%

    No Known Activations