© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30664
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to comparisons

    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_7_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
    {
    1.42
    (“
    1.08
    {//
    1.04
     angrily
    1.03
    \
    1.02
    <
    0.98
    
    0.96
     Elektrokh
    0.95
    {'
    0.94
    \";
    0.93
    POSITIVE LOGITS
     is
    1.40
    1.07
    و
    1.04
    .
    1.03
     The
    0.98
     in
    0.95
    и
    0.92
    ре
    0.89
    కు
    0.88
    ка
    0.88
    Activations Density 0.018%

    No Known Activations