© 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. 3590
    Prev
    Next
    INDEX
    Explanations

    socket

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    }$)
    0.55
    ‾
    0.55
    🦟
    0.55
     insectes
    0.53
    м
    0.52
    𝓉
    0.52
     bioquímica
    0.52
    𝖘
    0.51
    𝓈
    0.51
    nas
    0.51
    POSITIVE LOGITS
    ினேன்
    0.51
     المُ
    0.46
    ided
    0.46
    鏈
    0.46
     پھر
    0.45
    gag
    0.45
    ின
    0.44
     Cosa
    0.43
    ٕ
    0.42
    zeitig
    0.42
    Activations Density 0.002%

    No Known Activations