© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13864
    Prev
    Next
    INDEX
    Explanations

    prompt engineering

    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
    λλ
    0.57
    哪
    0.57
    ﻝ
    0.56
    所以
    0.54
     hỏi
    0.52
    你
    0.52
    ?“
    0.51
    ▌
    0.51
     IDF
    0.51
     kac
    0.50
    POSITIVE LOGITS
    ется
    0.55
    ైన
    0.52
    avlja
    0.52
     />);
    0.51
    os
    0.50
    ásico
    0.50
     handles
    0.50
    ются
    0.49
    지
    0.48
    าน
    0.47
    Activations Density 0.010%

    No Known Activations