© 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. 260734
    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
    あれば
    1.41
    同一个
    1.31
    情
    1.28
    Ę
    1.27
    情的
    1.27
    稱為
    1.23
    するため
    1.22
     slip
    1.21
    Ꮅ
    1.21
     rangka
    1.20
    POSITIVE LOGITS
    agic
    1.21
    TAIN
    1.20
    ʰ
    1.15
    ancial
    1.07
    𝓮
    1.04
    ሔ
    1.03
    द्दल
    1.03
    rivers
    1.02
    మూ
    1.02
    slate
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.