© 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. 76083
    Prev
    Next
    INDEX
    Explanations

    clean separation

    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
     EN
    0.33
     inadequate
    0.33
    destination
    0.33
     வித
    0.33
     അന്ത
    0.32
     ரொம்ப
    0.32
    Unter
    0.32
    š
    0.32
    Superview
    0.31
    OnInit
    0.31
    POSITIVE LOGITS
     pointers
    0.36
     evidenced
    0.35
     pure
    0.35
     savk
    0.34
     口
    0.34
     四
    0.33
    ynyl
    0.33
    纯
    0.33
     memo
    0.32
     ferro
    0.32
    Activations Density 0.007%

    No Known Activations