© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102225
    Prev
    Next
    INDEX
    Explanations

    controls the

    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_16_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
    绘制
    0.46
     indiquée
    0.46
    蚋
    0.45
    tım
    0.44
    ＰＥ
    0.43
    পুরের
    0.43
    蛞
    0.43
     فونبټ
    0.43
     моих
    0.43
    雩
    0.43
    POSITIVE LOGITS
     et
    0.63
     er
    0.57
     Luh
    0.54
     aber
    0.53
     Ober
    0.52
     in
    0.50
    isches
    0.49
     ober
    0.48
     einfacher
    0.48
     primul
    0.47
    Activations Density 0.000%

    No Known Activations