© 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. 6702
    Prev
    Next
    INDEX
    Explanations

    model starting phrase

    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
    ن
    0.60
    न
    0.59
    𝗼
    0.57
    う
    0.54
    囂
    0.54
    قیم
    0.53
     брен
    0.53
    ન
    0.53
     люди
    0.52
    ์
    0.51
    POSITIVE LOGITS
    ный
    0.57
    a
    0.55
    izing
    0.50
    ется
    0.47
    an
    0.43
    лийн
    0.41
    গুপ্ত
    0.41
    the
    0.41
    newcommand
    0.41
    ECT
    0.40
    Activations Density 0.468%

    No Known Activations