© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211538
    Prev
    Next
    INDEX
    Explanations

    read

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     crucial
    0.48
     wichtigen
    0.47
    玖
    0.44
     مهم
    0.44
     waż
    0.43
    重要な
    0.42
     महत्त्वपूर्ण
    0.42
     important
    0.42
     wichtiger
    0.41
     vital
    0.41
    POSITIVE LOGITS
    Fill
    0.42
    Aut
    0.41
    raine
    0.40
    Plain
    0.39
    Greet
    0.38
    Mitt
    0.38
    >("
    0.37
    Fine
    0.36
    Mees
    0.36
    ↵
    0.36
    Activations Density 0.005%

    No Known Activations