© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5034
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
    во
    1.99
    ב
    1.96
    dni
    1.96
    з
    1.83
    quoi
    1.81
     gostaria
    1.79
    ণী
    1.75
    вото
    1.74
    IVE
    1.72
    achable
    1.72
    POSITIVE LOGITS
     QtWidgets
    2.04
     программи
    1.97
     utterances
    1.85
     Shining
    1.85
    ➢
    1.83
     stup
    1.82
     extérieur
    1.81
     averted
    1.81
    AsyncKeyState
    1.78
    ইংরেজি
    1.75
    Activations Density 0.103%

    No Known Activations