© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50710
    Prev
    Next
    INDEX
    Explanations

    particle size

    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_31_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
    ポケット
    0.39
     پورے
    0.38
     গের
    0.38
     слот
    0.37
    範圍
    0.37
     naz
    0.37
     言
    0.37
    Divider
    0.36
    銃
    0.36
    国道
    0.35
    POSITIVE LOGITS
     horizon
    0.37
    โทร
    0.36
    秸
    0.36
    neh
    0.34
    got
    0.34
    rec
    0.34
    vpn
    0.34
     अंक
    0.34
    remote
    0.34
     pensions
    0.33
    Activations Density 0.054%

    No Known Activations