© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8979
    Prev
    Next
    INDEX
    Explanations

    vertical movement and changes

    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_13_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
    lc
    0.50
    声
    0.46
    Stat
    0.43
     энерго
    0.43
     आवाज
    0.42
     குர
    0.42
    <0x0D>
    0.41
     giọng
    0.40
    asta
    0.40
    క్త
    0.40
    POSITIVE LOGITS
     Catholicism
    0.46
     Dham
    0.45
     krijgen
    0.43
     $€
    0.43
     Πε
    0.42
     quieren
    0.42
     Rockets
    0.42
    ोरेंट
    0.41
     bekommen
    0.41
    ুরুর
    0.41
    Activations Density 0.022%

    No Known Activations