© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1078
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ت
    3.13
    aal
    3.09
    aarr
    2.97
    ឍ
    2.88
    र
    2.82
    ties
    2.79
    ة
    2.77
    తో
    2.76
    يا
    2.70
    tura
    2.69
    POSITIVE LOGITS
    ്
    3.85
    ש
    3.53
    да
    3.43
    withstanding
    3.26
    त
    2.99
    ب
    2.86
    v
    2.80
    oretical
    2.77
     erst
    2.77
    ρα
    2.73
    Activations Density 0.097%

    No Known Activations