© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164526
    Prev
    Next
    INDEX
    Explanations

    various verb forms and articles

    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_13_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
     d
    0.74
     )
    0.70
     Strikes
    0.64
     Island
    0.64
    وني
    0.62
     );
    0.60
     Hitler
    0.60
     .)
    0.60
     n
    0.58
     in
    0.57
    POSITIVE LOGITS
    Rg
    0.50
    Thickness
    0.49
     ხელ
    0.48
    idać
    0.47
    getKeyCode
    0.47
    க்கல்
    0.47
    ִי
    0.47
     scram
    0.47
    ㄽ
    0.47
    <
    0.46
    Activations Density 0.001%

    No Known Activations