© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198266
    Prev
    Next
    INDEX
    Explanations

    attribute assignment in object initialization

    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_27_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
     Anne
    0.40
    પો
    0.37
    피
    0.37
    目标
    0.37
     Premises
    0.36
    帯
    0.36
    𝘁
    0.35
    ㄱ
    0.35
    लग
    0.35
    政治
    0.34
    POSITIVE LOGITS
     rekonstru
    0.43
     côté
    0.41
     parametri
    0.39
    thisComponent
    0.39
     circol
    0.39
     contrario
    0.39
    initWith
    0.39
     théor
    0.38
    কাণ্ড
    0.38
    segn
    0.38
    Activations Density 0.001%

    No Known Activations