© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178594
    Prev
    Next
    INDEX
    Explanations

    time and numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Gain
    0.44
    Control
    0.40
    etest
    0.40
    ˳
    0.39
    <0x8A>
    0.38
    Anders
    0.37
     Gain
    0.37
    Prime
    0.37
     ETS
    0.37
    ITS
    0.37
    POSITIVE LOGITS
     hinged
    0.40
    ár
    0.39
     HB
    0.39
    ernes
    0.39
    萧
    0.38
     jabs
    0.38
     Ker
    0.38
     Dé
    0.37
     vip
    0.37
     چاہی
    0.37
    Activations Density 0.001%

    No Known Activations