© 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. 231358
    Prev
    Next
    INDEX
    Explanations

    pool noodles and bean bags

    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
    i
    0.96
    as
    0.91
    AN
    0.84
    in
    0.84
    да
    0.83
    os
    0.82
    jar
    0.82
    st
    0.81
    شن
    0.81
    met
    0.80
    POSITIVE LOGITS
    ع
    0.93
    }{*}{}
    0.90
     раствор
    0.88
     〢
    0.86
     сообщи
    0.85
     🌱
    0.84
     сдела
    0.82
     powied
    0.82
    0.80
     стаўкі
    0.79
    Activations Density 0.000%

    No Known Activations