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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2397
    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
    ्स
    2.72
    də
    2.47
    ్యాచ్
    2.41
    醐
    2.37
     pouvons
    2.35
    Мо
    2.35
    mouseX
    2.34
     betrayed
    2.33
     spä
    2.28
     precum
    2.27
    POSITIVE LOGITS
    ৈতিক
    3.03
     behalf
    2.99
    merksam
    2.98
     الرغم
    2.92
    coprotein
    2.82
    ducted
    2.81
    乎
    2.79
    ان
    2.76
    ряду
    2.75
    ный
    2.70
    Activations Density 0.008%

    No Known Activations