© 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. 8706
    Prev
    Next
    INDEX
    Explanations

    crisis text line

    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
     arxiv
    3.21
    𝓉
    2.97
    inputStream
    2.81
    𝘤
    2.76
     morphine
    2.75
    toon
    2.69
     pairwise
    2.66
     butterflies
    2.66
    𝑒
    2.66
     `:`
    2.62
    POSITIVE LOGITS
    ne
    2.57
    ギリス
    2.53
    ві
    2.53
    ्स
    2.46
    א
    2.39
    पाली
    2.39
    ز
    2.38
    咙
    2.37
    se
    2.36
    אנ
    2.36
    Activations Density 0.010%

    No Known Activations