© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11597
    Prev
    Next
    INDEX
    Explanations

    emphasis or affirmation

    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_13_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
    ASTIC
    0.59
     הל
    0.55
    宪
    0.54
    är
    0.54
     Características
    0.54
     среднем
    0.53
    𝕕
    0.53
     rekao
    0.53
     дней
    0.52
    Assertion
    0.52
    POSITIVE LOGITS
     isomerization
    0.57
     immuno
    0.57
     multipurpose
    0.54
    \
    0.53
    {
    0.51
    น
    0.51
     journey
    0.51
     bulkhead
    0.51
     airborne
    0.50
    ภ
    0.50
    Activations Density 0.000%

    No Known Activations