© 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. 177265
    Prev
    Next
    INDEX
    Explanations

    durability

    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
     파인더
    0.41
    loyd
    0.37
    ront
    0.37
    lden
    0.36
    ಲೆಯ
    0.36
    Trou
    0.36
    हू
    0.36
    邁
    0.35
    Rena
    0.35
    HD
    0.35
    POSITIVE LOGITS
     dur
    3.03
    Dur
    2.64
     Dur
    2.59
     dura
    2.48
     dure
    2.47
    dur
    2.45
     DUR
    2.42
     Dura
    2.23
     durability
    1.91
     durs
    1.85
    Activations Density 0.001%

    No Known Activations