© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250059
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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_56_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
    राने
    0.37
    ኙ
    0.37
    ớp
    0.36
     ›
    0.35
    OLOG
    0.35
    ysen
    0.35
    单一
    0.35
    STANDING
    0.35
    냔
    0.34
    ర్గ
    0.34
    POSITIVE LOGITS
     temporarily
    0.39
    carry
    0.38
    parad
    0.35
    toned
    0.34
    Official
    0.34
    seven
    0.33
    adult
    0.33
    निष्ठ
    0.33
     legít
    0.33
     Officially
    0.33
    Activations Density 0.001%

    No Known Activations