© 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. 3545
    Prev
    Next
    INDEX
    Explanations

    code strings

    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
    t
    0.39
    n
    0.38
    gie
    0.36
    nD
    0.34
    pivot
    0.33
    nig
    0.32
    nih
    0.32
    
    0.32
    nivers
    0.32
    migrate
    0.31
    POSITIVE LOGITS
    з
    0.44
    প
    0.34
    ਟ
    0.34
    ট
    0.33
     pleasant
    0.33
     talent
    0.32
     समझाने
    0.32
    Най
    0.32
     billing
    0.31
    च
    0.31
    Activations Density 0.099%

    No Known Activations