© 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. 6289
    Prev
    Next
    INDEX
    Explanations

    larger

    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
    𝐫
    3.97
    𝐧
    3.68
    𝐬
    3.35
    𝐃
    3.21
    𝐭
    3.18
    𝐑
    3.16
    𝐞
    3.11
    𝐲
    3.06
    𝐍
    3.04
    𝐚
    3.04
    POSITIVE LOGITS
    ер
    4.17
    ка
    3.00
     полномо
    2.69
    ত
    2.67
     hace
    2.62
     мощность
    2.59
     তাহলে
    2.58
    য়
    2.55
    th
    2.54
     envol
    2.54
    Activations Density 0.090%

    No Known Activations