© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46869
    Prev
    Next
    INDEX
    Explanations

    question followed by punctuation

    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_3_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
    
    0.70
    과의
    0.70
    重要な
    0.68
    ونی
    0.68
    제곱
    0.68
     intents
    0.67
    により
    0.66
     ondas
    0.65
    )$.
    0.64
    ゐ
    0.64
    POSITIVE LOGITS
    ad
    1.13
    на
    1.13
    et
    1.04
    il
    0.94
    ot
    0.89
    ut
    0.87
    al
    0.86
    ap
    0.86
    то
    0.80
    id
    0.79
    Activations Density 0.012%

    No Known Activations