© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143075
    Prev
    Next
    INDEX
    Explanations

    wallpaper or FACTOR

    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_0_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
    are
    2.31
     are
    2.27
    é
    1.88
     to
    1.68
    ка
    1.67
    та
    1.64
    ки
    1.61
    ва
    1.52
    ai
    1.47
    ك
    1.45
    POSITIVE LOGITS
    お
    1.52
    ᱗
    1.43
    Α
    1.41
    д
    1.35
    ৭
    1.35
    ндо
    1.34
    ר
    1.33
    糺
    1.30
    ار
    1.29
    お知らせ
    1.29
    Activations Density 0.000%

    No Known Activations