© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227630
    Prev
    Next
    INDEX
    Explanations

    launch product

    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_6_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
    การ
    1.01
    is
    0.95
     instit
    0.92
    ش
    0.89
     el
    0.88
     ".")
    0.83
     antidepressants
    0.82
     up
    0.81
     DIG
    0.81
     CIRC
    0.80
    POSITIVE LOGITS
    و
    0.96
    ين
    0.89
    もら
    0.89
    с
    0.85
    ዶች
    0.83
    도
    0.83
    ρου
    0.82
    нда
    0.82
    мени
    0.82
    ్య
    0.81
    Activations Density 0.001%

    No Known Activations