© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249796
    Prev
    Next
    INDEX
    Explanations

    Coordinated

    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_56_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
    struck
    0.40
     IUnary
    0.36
    stem
    0.35
    間に
    0.34
     giữa
    0.34
    咳
    0.33
     बदला
    0.33
     derog
    0.33
    ROTTLE
    0.33
    FERRED
    0.33
    POSITIVE LOGITS
     "
    0.46
     mord
    0.45
    Mord
    0.45
    ird
    0.43
     Ford
    0.40
     '
    0.40
     Mord
    0.40
     Shoes
    0.39
    ood
    0.38
    Ford
    0.38
    Activations Density 0.000%

    No Known Activations