© 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. 949
    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
    ا
    1.42
    a
    1.31
    ايا
    1.26
    𝙉
    0.99
     Narr
    0.99
    𝙋
    0.99
     emble
    0.97
    Narr
    0.96
    an
    0.95
     Emp
    0.94
    POSITIVE LOGITS
    hydraz
    1.13
    mousedown
    1.08
    랄
    1.06
    paragus
    1.00
     이건
    1.00
    荪
    0.97
     לי
    0.96
     Peki
    0.93
    לי
    0.93
     społ
    0.91
    Activations Density 0.000%

    No Known Activations