© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7546
    Prev
    Next
    INDEX
    Explanations

    fine-tuning or references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_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
     OSError
    1.20
    );}
    1.17
     জন্য
    1.16
    on
    1.15
    옛
    1.14
    hình
    1.14
    el
    1.09
    elves
    1.07
    sning
    1.06
    ../
    1.06
    POSITIVE LOGITS
    لي
    1.18
    िड
    1.10
    cribing
    1.08
    Whitelist
    1.02
     cbind
    1.00
    𝐆
    0.99
    टीसी
    0.98
    ilya
    0.97
     równ
    0.96
    みました
    0.96
    Activations Density 0.174%

    No Known Activations