© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14041
    Prev
    Next
    INDEX
    Explanations

    protective or possessive instincts

    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_15_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
     invigorating
    0.30
     forwarded
    0.28
    ሹ
    0.28
    FBSDKError
    0.27
     campagna
    0.27
     ấy
    0.27
    gaard
    0.27
    ierne
    0.27
     pept
    0.26
    fordern
    0.26
    POSITIVE LOGITS
    防
    0.28
     Data
    0.27
     VI
    0.27
     Play
    0.27
     Belg
    0.26
     protected
    0.26
     protective
    0.26
     ownership
    0.26
     Privacy
    0.25
     Wildlife
    0.25
    Activations Density 0.041%

    No Known Activations