© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245389
    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_11_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
    פ
    1.23
    umls
    1.16
    ંજ
    1.15
    Encycl
    1.15
    তাস
    1.15
    ە
    1.13
    Kü
    1.11
    FANG
    1.11
    arei
    1.11
    Brun
    1.10
    POSITIVE LOGITS
     emas
    1.31
     afterDir
    1.17
    ifizieren
    1.13
    ྕ
    1.11
     yarn
    1.10
    urndata
    1.10
     rezultat
    1.09
    此之外
    1.07
     hasil
    1.07
    ことは
    1.06
    Activations Density 0.000%

    No Known Activations