© 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. 161466
    Prev
    Next
    INDEX
    Explanations

    common occurrence

    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
    ق
    1.69
    מ
    1.65
    (
    1.48
    त
    1.45
    m
    1.41
    j
    1.41
    ত
    1.38
    ت
    1.35
    t
    1.34
    ס
    1.32
    POSITIVE LOGITS
     have
    1.31
    at
    1.05
    𝒔
    1.05
     де
    1.03
    ﺳ
    1.03
    ﺪ
    1.00
    တ်
    0.99
    ício
    0.99
    ız
    0.99
     présente
    0.98
    Activations Density 0.010%

    No Known Activations