© 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-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18531
    Prev
    Next
    INDEX
    Explanations

    code assignment `=`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
    trn
    0.38
     ইন্দ
    0.36
    審
    0.36
     sá
    0.35
    𝗴
    0.35
    葚
    0.35
    ANS
    0.34
    餃
    0.34
    gen
    0.34
     Giveaway
    0.34
    POSITIVE LOGITS
    anyon
    0.40
     qr
    0.39
    "=>
    0.39
     Robson
    0.38
    logne
    0.37
    一口
    0.37
     hereof
    0.37
     '*',
    0.36
     historique
    0.36
    óticos
    0.36
    Activations Density 0.033%

    No Known Activations