© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129331
    Prev
    Next
    INDEX
    Explanations

    as we

    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_6_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
    political
    0.97
    س
    0.86
    <0x9B>
    0.80
    с
    0.78
    <0x93>
    0.74
    <0xA5>
    0.72
    Theater
    0.72
    <0x82>
    0.71
    int
    0.71
    送
    0.70
    POSITIVE LOGITS
     buffs
    0.96
    し
    0.96
     chatbots
    0.93
     eks
    0.93
    at
    0.92
     utilisateur
    0.92
     to
    0.90
     amu
    0.89
     l
    0.89
     infall
    0.89
    Activations Density 0.002%

    No Known Activations