© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157918
    Prev
    Next
    INDEX
    Explanations

    hepatic, periodic, iconic

    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_2_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
    ва
    1.21
    ри
    1.09
    ون
    1.07
    ના
    1.00
    ك
    0.95
    ні
    0.92
    ет
    0.86
    на
    0.84
    י
    0.84
    েন
    0.83
    POSITIVE LOGITS
    s
    0.87
    0
    0.84
    in
    0.80
    ation
    0.79
    ਆਂ
    0.79
     to
    0.76
     The
    0.76
    to
    0.75
     veio
    0.74
     preocup
    0.73
    Activations Density 0.002%

    No Known Activations