© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12159
    Prev
    Next
    INDEX
    Explanations

    pick up

    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_40_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
    drops
    0.43
     drops
    0.41
    Drops
    0.38
    潁
    0.37
     drop
    0.36
     Drop
    0.36
    许
    0.36
    gravity
    0.35
     Drops
    0.35
    許
    0.35
    POSITIVE LOGITS
     pickup
    2.38
     pick
    2.20
     Pickup
    2.19
     picked
    2.16
    pickup
    2.13
    Pickup
    2.09
     Pick
    2.06
    Pick
    2.06
     pickups
    2.06
    pick
    1.96
    Activations Density 0.091%

    No Known Activations