© 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. 108547
    Prev
    Next
    INDEX
    Explanations

    cod followed by ing or ers

    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_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
    <0x80>
    1.33
    ر
    1.05
    д
    0.98
     mínimo
    0.96
    ای
    0.95
    OL
    0.95
     želite
    0.95
     bruke
    0.94
    quadratic
    0.94
    IP
    0.93
    POSITIVE LOGITS
    \
    1.43
    ns
    1.22
    ני
    1.18
    1.18
    נו
    1.13
    ă
    1.05
     as
    1.02
    -
    1.02
     a
    0.99
    ll
    0.99
    Activations Density 0.001%

    No Known Activations