© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9141
    Prev
    Next
    INDEX
    Explanations

    pickup

    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
    אן
    0.39
     compressibility
    0.37
     uc
    0.36
    歼
    0.34
    rile
    0.33
    Append
    0.33
     جیسا
    0.33
    妘
    0.32
     Rus
    0.32
    肛
    0.31
    POSITIVE LOGITS
     pickup
    2.41
     Pickup
    2.20
    pickup
    2.16
    Pickup
    2.13
     pick
    2.11
     pickups
    2.09
     Pick
    1.92
    Pick
    1.92
    pick
    1.84
     PICK
    1.82
    Activations Density 0.061%

    No Known Activations