© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2251
    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
    ו
    1.96
    "{@
    1.70
     \<
    1.68
    \]
    1.54
    leaved
    1.53
    ahu
    1.53
    ]_
    1.51
    ى
    1.48
    oooo
    1.46
     deepening
    1.44
    POSITIVE LOGITS
    ના
    2.20
    ر
    1.70
    en
    1.65
    Полу
    1.60
     været
    1.56
     stup
    1.50
    пита
    1.49
    Advertisement
    1.49
    𝙞
    1.47
    eram
    1.46
    Activations Density 0.008%

    No Known Activations