© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216417
    Prev
    Next
    INDEX
    Explanations

    expecting

    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_31_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
    getProgress
    0.40
     optic
    0.40
    =@@
    0.38
     고민
    0.38
     odour
    0.38
                
    0.37
     మే
    0.37
    entiary
    0.37
    同志
    0.37
    __*/
    0.36
    POSITIVE LOGITS
     Expect
    0.48
    Expect
    0.47
     expect
    0.45
     oček
    0.41
     एक्सपेक्ट
    0.39
    expects
    0.36
    EXPECT
    0.36
     Expected
    0.36
     دقی
    0.36
    expect
    0.36
    Activations Density 0.001%

    No Known Activations