© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46569
    Prev
    Next
    INDEX
    Explanations

    cloud-native technologies

    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_3_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
    은
    0.97
    사
    0.89
    は
    0.82
     in
    0.81
    w
    0.79
    도
    0.79
     metastases
    0.76
    ह
    0.75
    在
    0.73
    কে
    0.71
    POSITIVE LOGITS
    kelijke
    0.65
    ンテ
    0.64
    gled
    0.64
    gelijk
    0.62
    gericht
    0.59
    gewicht
    0.59
    ンジ
    0.58
    hendis
    0.57
    dogan
    0.55
    嫚
    0.55
    Activations Density 0.002%

    No Known Activations