© 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. 3893
    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
    an
    2.37
    なんと
    2.19
    𝗵
    2.10
    :][
    2.09
    செய்ய
    2.07
     जीता
    2.01
    निज
    1.99
     саме
    1.97
    Applicants
    1.97
    了一个
    1.96
    POSITIVE LOGITS
    ية
    3.02
    ść
    2.89
    জনের
    2.82
     việc
    2.52
    ار
    2.48
    UAGE
    2.41
    पी
    2.41
    ר
    2.29
     Ă
    2.28
    MING
    2.28
    Activations Density 0.104%

    No Known Activations