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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6834
    Prev
    Next
    INDEX
    Explanations

    gradient accumulation and checkpointing

    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_40_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
    काम
    0.38
    丧
    0.38
     egress
    0.37
    ही
    0.36
     hay
    0.36
    драв
    0.36
    मुना
    0.36
    Reached
    0.35
     Anya
    0.35
     Tenant
    0.35
    POSITIVE LOGITS
    步骤
    0.43
    潴
    0.42
    step
    0.42
    accumulation
    0.40
    steps
    0.40
     accumulation
    0.38
    Bước
    0.38
    ວກ
    0.37
    स्टेप
    0.37
    Accum
    0.37
    Activations Density 0.004%

    No Known Activations