© 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. 2970
    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
     able
    3.14
    然後
    2.81
     simplify
    2.49
    সকল
    2.46
    uZ
    2.36
    Дан
    2.35
     SIINFEKL
    2.34
    ১
    2.32
     contending
    2.26
    ваний
    2.25
    POSITIVE LOGITS
     else
    3.10
    ية
    2.99
    ه
    2.66
     terren
    2.57
    ীয়
    2.53
     yerde
    2.52
     tyre
    2.50
    THING
    2.50
     anderes
    2.46
    ள்ளது
    2.45
    Activations Density 0.007%

    No Known Activations