© 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. 5509
    Prev
    Next
    INDEX
    Explanations

    ATX Mid-Tower Case

    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
     образом
    1.37
    म
    1.33
    প্র
    1.08
    ασ
    1.05
    <0xA1>
    1.04
     conformations
    1.02
     voorzien
    1.00
     trata
    0.99
    ми
    0.99
    तिहासिक
    0.98
    POSITIVE LOGITS
    g
    0.97
    et
    0.94
    traj
    0.93
    cional
    0.91
    ''''
    0.91
    uje
    0.89
    leme
    0.87
    gam
    0.87
    ĭ
    0.86
    不变
    0.86
    Activations Density 0.001%

    No Known Activations