© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178063
    Prev
    Next
    INDEX
    Explanations

    `==`

    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_24_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
    [
    0.40
    yaj
    0.40
    쿠
    0.38
    առ
    0.36
     épa
    0.36
    郁
    0.36
     возра
    0.35
     계획
    0.35
    ég
    0.35
    mois
    0.35
    POSITIVE LOGITS
     wach
    0.45
    (".");
    0.44
     पहचानने
    0.43
    𝗘
    0.43
     exhausted
    0.42
     কম্পিউ
    0.41
     அடையாளம்
    0.41
     analyze
    0.41
     thisComponent
    0.40
    夻
    0.40
    Activations Density 0.001%

    No Known Activations