© 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. 6975
    Prev
    Next
    INDEX
    Explanations

    president 44th the as served

    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
    𝐞
    1.45
    هایی
    1.38
    𝐬
    1.37
    𝐲
    1.37
    𝐨
    1.24
    <unused249>
    1.22
    𝐚
    1.20
    ে
    1.19
    σταν
    1.18
    𝐒
    1.16
    POSITIVE LOGITS
    д
    1.17
    х
    1.12
    Воз
    1.12
    ̣n
    1.05
    ils
    1.00
     elet
    0.97
    gi
    0.96
    kek
    0.95
    to
    0.94
    isActive
    0.93
    Activations Density 0.001%

    No Known Activations