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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3305
    Prev
    Next
    INDEX
    Explanations

    hashtags

    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
    াৎ
    0.60
    魎
    0.52
     lintas
    0.49
     metamorph
    0.48
     napp
    0.47
    та
    0.47
    
    0.46
    insieme
    0.46
     locomotion
    0.46
     сус
    0.46
    POSITIVE LOGITS
    ل
    0.59
     oč
    0.59
     Tämä
    0.58
    ৯
    0.58
    тся
    0.58
    أ
    0.54
    鐺
    0.54
    メント
    0.54
     esposa
    0.53
    മു
    0.53
    Activations Density 0.007%

    No Known Activations