© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3585
    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_5_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
    ে
    1.58
     शिक्ष
    1.57
     giveaway
    1.54
    usize
    1.53
    гі
    1.51
     phụ
    1.50
     yell
    1.49
     khuyến
    1.49
    ът
    1.49
    ᱾
    1.45
    POSITIVE LOGITS
    mals
    1.76
    nable
    1.74
    ด์
    1.72
    드
    1.71
     vergang
    1.64
    нили
    1.63
    faction
    1.61
    THING
    1.59
    enumer
    1.59
     Pourquoi
    1.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.