© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193787
    Prev
    Next
    INDEX
    Explanations

    focused periods or bursts

    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_4_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
    د
    0.55
     schwierig
    0.49
    ítě
    0.48
    转型
    0.47
     사용하는
    0.46
     vivent
    0.45
    ข้อง
    0.45
    stücke
    0.45
     오랜
    0.44
    -//
    0.44
    POSITIVE LOGITS
    on
    0.54
     is
    0.51
     puesto
    0.50
     haci
    0.41
     slaughter
    0.41
    ﮧ
    0.40
    ES
    0.40
    out
    0.40
    S
    0.40
    park
    0.39
    Activations Density 0.000%

    No Known Activations