© 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. 6514
    Prev
    Next
    INDEX
    Explanations

    File System System actions

    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
    een
    2.67
    eine
    2.32
    у
    2.29
    સ
    2.29
    𝐲
    2.15
     facendo
    2.14
    𝐧
    2.14
    fichier
    2.05
    econ
    2.04
    eh
    2.01
    POSITIVE LOGITS
    ли
    1.97
     установ
    1.93
    ках
    1.91
     atracción
    1.84
    가
    1.83
    іль
    1.81
    selves
    1.79
    MENTS
    1.76
     ity
    1.74
     із
    1.72
    Activations Density 0.006%

    No Known Activations