© 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. 254
    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
    У
    0.86
    ছিলাম
    0.83
    Ι
    0.77
     Auch
    0.76
    Empty
    0.76
    u
    0.74
    지금
    0.74
    ي
    0.71
    ছিল
    0.71
    ме
    0.70
    POSITIVE LOGITS
    时候
    1.20
    ية
    1.13
     supposed
    1.03
     blevet
    0.89
     물론
    0.87
    wolves
    0.87
    quasi
    0.86
     गोइंग
    0.84
     able
    0.83
    наў
    0.80
    Activations Density 1.333%

    No Known Activations