© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3364
    Prev
    Next
    INDEX
    Explanations

    Also, followed by comma

    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_5_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
    م
    2.76
    ిన
    2.13
    ことなく
    2.02
    مح
    1.93
    ن
    1.88
     suốt
    1.87
    isjon
    1.87
    س
    1.78
    osphäre
    1.68
     Originally
    1.68
    POSITIVE LOGITS
    ˆ‚
    1.93
     fighters
    1.68
     snack
    1.58
    ｒ
    1.52
     biographer
    1.49
     sniper
    1.48
    檚
    1.48
     redist
    1.48
     snacking
    1.46
     rangers
    1.45
    Activations Density 0.008%

    No Known Activations