© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8612
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ва
    2.67
    ल
    2.61
    р
    2.57
     כך
    2.55
    х
    2.50
    ˈ
    2.41
     ljud
    2.30
     striis
    2.25
     subjecting
    2.22
    ির
    2.21
    POSITIVE LOGITS
    要
    2.75
    要知道
    2.64
     biggest
    2.46
    rically
    2.42
    citing
    2.41
    没
    2.41
    '^
    2.39
     vẻ
    2.36
    इसके
    2.36
    知道
    2.33
    Activations Density 0.045%

    No Known Activations