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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210333
    Prev
    Next
    INDEX
    Explanations

    gradient clipping and accumulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_19_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
    実感
    0.46
     osa
    0.45
    ]
    0.44
     Isa
    0.44
    )
    0.44
    叼
    0.44
    )]
    0.43
     mr
    0.42
     zuverläss
    0.42
     ISA
    0.42
    POSITIVE LOGITS
    敛
    0.46
     같은
    0.46
    TextBoxColumn
    0.45
    şti
    0.44
     தேசிய
    0.44
    παϊ
    0.44
    Aggregation
    0.44
    िफिशियल
    0.43
     패턴
    0.42
    聚
    0.42
    Activations Density 0.001%

    No Known Activations