© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    tell me:

    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
    𝐯
    1.20
    𝐲
    1.10
    𝐭
    1.09
    𝐥
    1.05
    годно
    1.03
     meaningless
    1.02
     unimaginable
    1.01
    henes
    0.99
    ুঁ
    0.99
     Qxf
    0.98
    POSITIVE LOGITS
    가
    1.01
    um
    0.91
    录
    0.83
     chút
    0.79
    いる
    0.78
    ه
    0.78
     conduit
    0.77
     нюан
    0.76
    ownership
    0.74
    नई
    0.74
    Activations Density 0.042%

    No Known Activations