© 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
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44015
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical operations

    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_3_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
    at
    1.09
    r
    0.95
    in
    0.87
    s
    0.84
    as
    0.82
    ת
    0.77
    er
    0.77
    ab
    0.74
    (
    0.74
    GPa
    0.74
    POSITIVE LOGITS
     σημαν
    0.82
     га
    0.80
     прове
    0.80
     champs
    0.73
     not
    0.72
     студен
    0.72
     συμβ
    0.72
    َ
    0.71
    場合に
    0.71
     гене
    0.69
    Activations Density 0.026%

    No Known Activations