© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195937
    Prev
    Next
    INDEX
    Explanations

    lajcsi

    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_4_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
    {
    1.20
    ط
    1.13
    (
    1.11
    리
    1.09
    ла
    0.98
    يا
    0.96
    বে
    0.94
    يل
    0.94
     hermoso
    0.93
     Espanha
    0.93
    POSITIVE LOGITS
    s
    1.41
    et
    1.03
    A
    0.98
    ंना
    0.93
    in
    0.92
    ,
    0.91
    You
    0.91
    at
    0.90
    and
    0.88
    ating
    0.88
    Activations Density 0.000%

    No Known Activations