© 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. 35516
    Prev
    Next
    INDEX
    Explanations

    flex-direction

    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
    förm
    0.42
    microseconds
    0.38
    吒
    0.37
    葷
    0.37
     अभ्यर्थ
    0.36
    娑
    0.36
    regions
    0.35
     مثبت
    0.35
    
    0.35
    formatter
    0.35
    POSITIVE LOGITS
    匱
    0.39
     slot
    0.38
     Ammonium
    0.37
    ביר
    0.36
     Algebraic
    0.36
     Reverse
    0.35
     quantity
    0.35
    憎
    0.35
     lives
    0.35
    匮
    0.34
    Activations Density 0.004%

    No Known Activations