© 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. 20062
    Prev
    Next
    INDEX
    Explanations

    hockey terms

    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
     cle
    0.40
     गीता
    0.37
    システム
    0.37
    üse
    0.36
    ics
    0.36
     पौ
    0.35
     줄
    0.35
    帙
    0.35
    აცი
    0.33
    MCA
    0.33
    POSITIVE LOGITS
     Stanley
    0.94
    Stanley
    0.88
     Sidney
    0.78
     stick
    0.71
    Bru
    0.71
     Norris
    0.70
    Leaf
    0.65
     sticks
    0.64
    bru
    0.64
     Stick
    0.63
    Activations Density 0.006%

    No Known Activations