© 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. 3792
    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
    醐
    3.18
    しかも
    2.99
     ObjectMapper
    2.79
    istically
    2.75
    ش
    2.74
    ви
    2.69
     ′
    2.63
     стоит
    2.61
     been
    2.61
     spinal
    2.60
    POSITIVE LOGITS
     fact
    3.30
    er
    3.28
    ের
    3.12
    o
    3.10
    ी
    3.06
    s
    3.05
     aise
    3.03
    𝘀
    2.91
    ে
    2.87
    lamak
    2.79
    Activations Density 0.050%

    No Known Activations