© 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
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203562
    Prev
    Next
    INDEX
    Explanations

    pacific rim, theater, plate, time

    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_6_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
    asambhavam
    1.29
     Име
    1.27
     Ак
    1.11
    embeddings
    1.11
     Ам
    1.10
     Α
    1.09
     Τ
    1.08
     Ευ
    1.08
     Ар
    1.07
     Аль
    1.07
    POSITIVE LOGITS
    -
    1.31
    .
    1.30
    י
    0.95
     steel
    0.92
     glass
    0.92
     n
    0.91
     on
    0.90
    ↵↵
    0.85
     green
    0.83
     paper
    0.83
    Activations Density 0.000%

    No Known Activations