© 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. 162032
    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_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
     was
    1.57
     is
    1.35
     be
    1.31
    aj
    1.30
    s
    1.24
    ?
    1.19
    .
    1.13
     are
    1.12
     you
    1.09
     can
    1.08
    POSITIVE LOGITS
    ень
    0.98
    یت
    0.93
    क्राइब
    0.91
    ことができます
    0.91
    uciones
    0.88
     costitu
    0.87
    슨
    0.86
    ισ
    0.86
    ږئ
    0.85
    ಸ್ಕೊ
    0.85
    Activations Density 0.000%

    No Known Activations