© 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. 7063
    Prev
    Next
    INDEX
    Explanations

    Show, Don't Tell

    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
    на
    3.24
    u
    2.89
    𝗂
    2.54
    𝗄
    2.50
    𝗈
    2.48
    𝖾
    2.31
     dislocation
    2.26
     hatches
    2.24
    𝖺
    2.22
    ский
    2.20
    POSITIVE LOGITS
    ة
    2.62
    唆
    2.24
    ни
    2.24
    stopping
    2.24
    hafte
    2.20
    turtle
    2.17
    stopper
    2.14
    сць
    2.12
    ت
    2.10
    ed
    2.07
    Activations Density 0.010%

    No Known Activations