© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157116
    Prev
    Next
    INDEX
    Explanations

    Saarbrücken, Rosalind, acks

    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_2_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
    3
    1.20
    т
    1.18
     by
    1.01
     or
    0.95
    ت
    0.92
    at
    0.91
    𝟯
    0.87
    dür
    0.85
    lar
    0.85
    lerce
    0.84
    POSITIVE LOGITS
     It
    1.38
    不
    1.37
    你
    1.35
    It
    1.33
    问题
    1.23
    س
    1.20
    İ
    1.18
    它
    1.14
    та
    1.11
    我
    1.08
    Activations Density 0.000%

    No Known Activations