© 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. 382
    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
     inverse
    0.44
    tob
    0.43
     došlo
    0.41
    𝙴
    0.40
     indemnity
    0.40
    ಸ್‌
    0.40
    స్‌
    0.40
    यों
    0.39
     pierwsze
    0.39
    sorry
    0.39
    POSITIVE LOGITS
     AUC
    0.46
     tenu
    0.44
    ى
    0.41
    หมู่
    0.40
    пит
    0.40
    を果た
    0.38
    е
    0.38
    gers
    0.37
     tandem
    0.37
    ்ப
    0.36
    Activations Density 1.322%

    No Known Activations