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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9134
    Prev
    Next
    INDEX
    Explanations

    grids and nets

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     Compd
    0.67
     contractions
    0.67
     lahan
    0.64
    semi
    0.63
    생
    0.62
     semi
    0.62
    山市
    0.62
     Crowe
    0.61
    erosion
    0.61
     সংকো
    0.59
    POSITIVE LOGITS
     bars
    1.86
     net
    1.57
     bar
    1.54
     grids
    1.50
     mesh
    1.49
     nets
    1.49
     grid
    1.48
    网
    1.45
    bars
    1.45
     Net
    1.44
    Activations Density 0.129%

    No Known Activations