© 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. 2887
    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
     irrespective
    2.50
    ோ
    2.44
    sortie
    2.44
    мер
    2.42
    べき
    2.40
    drinking
    2.39
     damn
    2.38
     discrete
    2.35
     redeem
    2.34
    thing
    2.32
    POSITIVE LOGITS
    ی
    2.55
     pues
    2.40
     рост
    2.23
     سازی
    2.11
    𝙨
    2.07
     construe
    2.03
     createdAt
    2.01
    }$$
    2.00
     zbog
    1.99
    চী
    1.97
    Activations Density 0.003%

    No Known Activations