© 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. 127
    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
     ine
    1.07
     wandering
    0.91
     careful
    0.90
     Ө
    0.90
     probs
    0.89
    LSTM
    0.89
     avail
    0.88
     preferably
    0.87
    fluence
    0.87
     chutney
    0.86
    POSITIVE LOGITS
    د
    1.07
    сть
    1.05
    ity
    1.04
    دون
    0.94
    داد
    0.89
    κ
    0.88
    𝗇
    0.86
    kan
    0.86
    𝚊
    0.83
    者
    0.83
    Activations Density 0.007%

    No Known Activations