© 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. 79350
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    2.36
    _
    2.02
    an
    1.99
    ד
    1.81
    t
    1.74
    0
    1.74
    ۱
    1.70
    া
    1.70
     a
    1.66
    ти
    1.60
    POSITIVE LOGITS
    ных
    1.65
     to
    1.58
    ع
    1.34
    és
    1.31
    ührt
    1.27
    ão
    1.26
    ется
    1.26
    angs
    1.23
    بن
    1.11
    nement
    1.10
    Activations Density 0.000%

    No Known Activations