© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89526
    Prev
    Next
    INDEX
    Explanations

    import

    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_23_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
     filha
    0.44
     filhos
    0.39
    咨
    0.39
     earthen
    0.39
     daughters
    0.38
    ambuf
    0.38
     అది
    0.38
     وفا
    0.38
     watery
    0.38
     reve
    0.37
    POSITIVE LOGITS
     இரண்டு
    0.44
     Mạnh
    0.43
     Manganese
    0.40
     Manipulation
    0.40
     Kunden
    0.39
    叄
    0.39
     Crawler
    0.38
    aneously
    0.38
     iki
    0.38
     انٹر
    0.38
    Activations Density 0.000%

    No Known Activations