© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8440
    Prev
    Next
    INDEX
    Explanations

    matplotlib.pyplot as plt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ﻼ
    2.88
    Đáp
    2.42
    एँ
    2.34
    ﺮ
    2.32
    ﻞ
    2.31
    MainBinding
    2.31
    أ
    2.30
    ﻨ
    2.29
    áles
    2.28
    此之外
    2.27
    POSITIVE LOGITS
    р
    2.75
    n
    2.52
    an
    2.47
    mehr
    2.25
    messageInfo
    2.21
     scipy
    2.21
    nahme
    2.20
    야
    2.20
     شہادت
    2.16
    vidia
    2.13
    Activations Density 0.001%

    No Known Activations