© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6552
    Prev
    Next
    INDEX
    Explanations

    helpline numbers

    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
    و
    4.59
    ו
    3.67
    一个
    2.95
    স
    2.78
    et
    2.59
    al
    2.53
    다음
    2.51
    क
    2.48
    ım
    2.45
    or
    2.26
    POSITIVE LOGITS
    𝑠
    3.02
    𝑓
    2.85
    InOut
    2.80
    ومن
    2.64
    ьте
    2.64
    𝑔
    2.61
    𝑑
    2.45
    𝑎
    2.43
    ﻪ
    2.40
     ruin
    2.33
    Activations Density 0.038%

    No Known Activations