© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260472
    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_10_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
     madness
    1.32
     joys
    1.28
    𝑙
    1.27
     insanity
    1.25
     frenzy
    1.22
     defeating
    1.21
     chopping
    1.21
     stretches
    1.21
    Ɔ
    1.20
    鈮
    1.19
    POSITIVE LOGITS
    ين
    1.45
     trudno
    1.23
     natomiast
    1.22
    ب
    1.20
    Lion
    1.16
    train
    1.15
     fárm
    1.14
    ум
    1.13
     istnie
    1.11
    یا
    1.10
    Activations Density 0.000%

    No Known Activations