© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50021
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     вещей
    0.47
     THINGS
    0.42
    oides
    0.42
    oid
    0.40
     ነገ
    0.39
    🙋
    0.38
    Things
    0.38
     कहकर
    0.38
    📃
    0.37
    キュリティ
    0.37
    POSITIVE LOGITS
     extreme
    0.62
     high
    0.59
     moderate
    0.57
    extreme
    0.57
     высокие
    0.54
    Extreme
    0.53
     altas
    0.52
    Moderate
    0.52
    high
    0.52
     excessive
    0.51
    Activations Density 0.011%

    No Known Activations