© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170473
    Prev
    Next
    INDEX
    Explanations

    math function 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
     функ
    0.42
    ’
    0.38
     функцию
    0.38
    所属
    0.38
     아니다
    0.37
    IRED
    0.37
     ఏడాది
    0.36
     বিপ্লবী
    0.35
    functional
    0.34
    PED
    0.34
    POSITIVE LOGITS
    Prefix
    0.40
    }{\
    0.39
    proximity
    0.37
    čnosti
    0.37
     Prefix
    0.35
    ˙
    0.35
     "?
    0.35
    撲
    0.35
    ](
    0.35
    હ
    0.35
    Activations Density 0.001%

    No Known Activations