© 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. 208743
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    landet
    0.38
    Won
    0.38
    MgCl
    0.38
    作为
    0.37
    म्र
    0.37
    Puede
    0.37
    Exceptionally
    0.36
    --
    0.36
    蜼
    0.36
    puede
    0.36
    POSITIVE LOGITS
     built
    0.55
     controlled
    0.53
     an
    0.50
     owned
    0.48
     Built
    0.48
     labeled
    0.45
     indicating
    0.44
     closing
    0.43
     agreeing
    0.43
     starting
    0.43
    Activations Density 0.005%

    No Known Activations