© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 1-GEMMASCOPE-2-TRANSCODER-262K
    4. 132201
    Prev
    Next
    INDEX
    Explanations

    Florida Board of

    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_1_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
    ,
    1.30
    и
    1.09
     comprehens
    1.07
    ସ
    1.02
    ppure
    0.99
     tenements
    0.98
    x
    0.98
    द
    0.98
    ш
    0.97
    на
    0.96
    POSITIVE LOGITS
     Plants
    1.05
    {
    1.02
    OL
    1.01
    (
    1.00
     Methyl
    0.95
     Uttarakhand
    0.95
     Pathways
    0.93
    एम
    0.92
     Directory
    0.91
     Measurements
    0.91
    Activations Density 0.001%

    No Known Activations