© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214893
    Prev
    Next
    INDEX
    Explanations

    Mountain Dew, Mountain Warehouse

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Sn
    0.45
     ker
    0.42
    要
    0.41
     Reli
    0.40
    イント
    0.38
    ́n
    0.37
    RIX
    0.37
    Sn
    0.36
    iyam
    0.36
     Abs
    0.36
    POSITIVE LOGITS
    ᠬ
    0.47
     ওয়াল
    0.40
    ploid
    0.40
    ITZ
    0.39
    wall
    0.38
     fresh
    0.38
    PCB
    0.37
    promises
    0.36
    onik
    0.36
     орга
    0.35
    Activations Density 0.000%

    No Known Activations