© 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. 5519
    Prev
    Next
    INDEX
    Explanations

    New Haven, Connecticut or Wands

    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
    𝗲
    0.87
    pte
    0.86
    prés
    0.86
    𝗶
    0.81
    𝗹
    0.79
    𝗴
    0.78
    Enfin
    0.77
    lere
    0.77
    𝗘
    0.76
    yal
    0.75
    POSITIVE LOGITS
    可以
    1.07
    р
    0.91
     তারপরে
    0.87
    可以让
    0.87
    و
    0.86
    お
    0.86
     ලද
    0.84
    אנ
    0.83
    つまり
    0.83
    此事
    0.80
    Activations Density 0.002%

    No Known Activations