© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88041
    Prev
    Next
    INDEX
    Explanations

    browser security

    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_23_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
     verhaal
    0.42
    ulo
    0.40
    unless
    0.39
     storytelling
    0.38
    ≔
    0.38
     angle
    0.38
    på
    0.37
    ulating
    0.37
    reading
    0.36
     давайте
    0.36
    POSITIVE LOGITS
    高于
    0.47
    नामी
    0.41
     پو
    0.41
    大于
    0.41
    จัก
    0.40
     мозга
    0.40
    밉
    0.40
    レクトリ
    0.38
    強く
    0.38
     பெயர்
    0.37
    Activations Density 0.004%

    No Known Activations