© 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. 3733
    Prev
    Next
    INDEX
    Explanations

    varying levels of detail

    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
     того
    1.26
     corrente
    1.24
    作用
    1.21
    el
    1.13
    <0x8F>
    1.08
     recourse
    1.06
    ச்ச
    1.06
    wedge
    1.05
     hatt
    1.04
    fromj
    1.02
    POSITIVE LOGITS
    ا
    1.96
     CEN
    1.44
    ्ञ
    1.35
    ir
    1.34
    া
    1.32
    ার্স
    1.30
    檬
    1.30
    вость
    1.29
    ৪২
    1.28
    ি
    1.28
    Activations Density 0.006%

    No Known Activations