© 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. 6601
    Prev
    Next
    INDEX
    Explanations

    condition

    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
     ------
    2.85
    cklen
    2.81
    an
    2.80
    ামুটি
    2.77
     газета
    2.74
    draggable
    2.71
    aldehyde
    2.69
    যদি
    2.65
    त्याने
    2.64
    zano
    2.63
    POSITIVE LOGITS
    WeakTable
    3.54
    y
    2.99
    ва
    2.92
    ра
    2.88
     préal
    2.84
    nement
    2.78
    ल
    2.72
     ezt
    2.69
     रूप
    2.67
     pral
    2.67
    Activations Density 0.017%

    No Known Activations