© 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. 6260
    Prev
    Next
    INDEX
    Explanations

    P/E ratio

    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
     leptonic
    2.04
    xan
    2.01
    v
    1.87
    nnnn
    1.80
    z
    1.76
     commas
    1.74
    vend
    1.72
     doings
    1.69
    NOMBRE
    1.67
    ویں
    1.67
    POSITIVE LOGITS
    𝐢
    2.12
    ी
    1.92
    𝗶
    1.91
    𝐨
    1.76
    ی
    1.69
    ம்
    1.65
    สอบ
    1.63
    ി
    1.60
    ت
    1.57
    ️
    1.55
    Activations Density 0.027%

    No Known Activations