© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5498
    Prev
    Next
    INDEX
    Explanations

    cutting-edge, Modern

    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_3_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
    на
    1.91
    紝
    1.89
    ीय
    1.86
    یل
    1.79
    彡
    1.77
     naman
    1.74
     хотя
    1.72
    یان
    1.71
    ח
    1.70
    鏄
    1.68
    POSITIVE LOGITS
     conveniences
    2.35
     addTo
    2.25
    ות
    2.22
     tume
    2.12
    𝘢
    2.10
    де
    2.06
    𝘥
    2.03
    nunique
    2.03
     amenities
    1.95
    ियोजना
    1.95
    Activations Density 0.096%

    No Known Activations