© 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. 161662
    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
    т
    1.82
    но
    1.65
    t
    1.59
    ви
    1.46
    -
    1.46
    ت
    1.35
    ?
    1.27
    ى
    1.27
    \
    1.27
    <0x0D>
    1.25
    POSITIVE LOGITS
    াদেশিক
    0.94
    in
    0.94
    setter
    0.94
    на
    0.91
    ഷ്ട്ര
    0.89
     Shipbuilding
    0.87
    濩
    0.86
     Versions
    0.85
    ма
    0.84
    ፈላጊ
    0.84
    Activations Density 0.000%

    No Known Activations