© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21479
    Prev
    Next
    INDEX
    Explanations

    sports actions

    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
     government
    0.41
     porta
    0.39
     amounting
    0.39
     bake
    0.38
     mars
    0.37
     baked
    0.37
     pass
    0.37
     p
    0.37
    אי
    0.37
     Truth
    0.37
    POSITIVE LOGITS
     defending
    1.46
     defend
    0.85
     defends
    0.83
     finishing
    0.75
     defended
    0.73
     Finishing
    0.66
     marking
    0.60
     Marking
    0.60
     attacking
    0.58
     Crossing
    0.58
    Activations Density 0.022%

    No Known Activations