© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83314
    Prev
    Next
    INDEX
    Explanations

    pleiotropy, anisotropy

    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_0_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
    a
    1.59
    า
    1.54
     The
    1.38
    りと
    1.38
    ه
    1.34
    ia
    1.33
    りたい
    1.32
    া
    1.31
    ा
    1.29
     była
    1.28
    POSITIVE LOGITS
    ri
    1.52
     изделия
    1.27
    ت
    1.27
     estadística
    1.26
    stas
    1.21
    ndez
    1.20
    зе
    1.19
     ética
    1.19
    lal
    1.15
    ጨማሪ
    1.15
    Activations Density 0.000%

    No Known Activations