© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6879
    Prev
    Next
    INDEX
    Explanations

    URLs, websites, organizations

    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
    چه
    0.51
    ので
    0.45
    ある
    0.43
     powodu
    0.43
    cnica
    0.42
     Dinge
    0.41
     paio
    0.40
    ്
    0.40
     речь
    0.39
    которые
    0.39
    POSITIVE LOGITS
    aż
    0.52
     mogul
    0.49
    
    0.47
    aa
    0.46
     conn
    0.46
     buck
    0.45
    s
    0.45
    ات
    0.45
    িয়া
    0.45
    نٹ
    0.44
    Activations Density 0.238%

    No Known Activations