© 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. 5397
    Prev
    Next
    INDEX
    Explanations

    daunting, plausible, or interesting followed by phrases

    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
     overcoming
    2.16
     retornar
    1.98
    至于
    1.85
    uje
    1.81
    𝘴
    1.80
    𝐂
    1.79
     sanguí
    1.78
     gleaming
    1.77
    jTextField
    1.77
    𝐍
    1.77
    POSITIVE LOGITS
    ület
    1.95
     tượng
    1.74
    nament
    1.70
     pēc
    1.69
     cotid
    1.67
    го
    1.65
    ingly
    1.64
     outset
    1.60
    тости
    1.59
    ोग
    1.56
    Activations Density 0.142%

    No Known Activations