© 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. 260234
    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
     enth
    1.20
     коне
    1.19
    \]
    1.14
    이렇게
    1.11
    ඟ
    1.10
     Народ
    1.06
     éventuellement
    1.05
     판매
    1.05
    즉
    1.03
     croissance
    1.03
    POSITIVE LOGITS
    aviti
    1.22
    രോധ
    1.14
    ゴン
    1.12
     kanggo
    1.11
    zonej
    1.11
     shirt
    1.10
    ऱ्या
    1.09
    𝚖
    1.09
     niya
    1.09
    ição
    1.08
    Activations Density 0.000%

    No Known Activations