© 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. 3459
    Prev
    Next
    INDEX
    Explanations

    move forward or beyond

    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
    SBP
    0.35
     fenómenos
    0.33
    𝗞
    0.33
    
    0.33
    ἥ
    0.32
    ھے
    0.31
     nostrum
    0.31
    ња
    0.30
     posteriori
    0.30
     précis
    0.30
    POSITIVE LOGITS
    ierung
    0.34
    此之外
    0.32
     proliferation
    0.30
    单击
    0.30
    意见
    0.29
    可以选择
    0.29
    alai
    0.29
     similarity
    0.28
    ोन
    0.28
    ي
    0.28
    Activations Density 0.009%

    No Known Activations