© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200660
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     považ
    0.39
     doença
    0.39
    rian
    0.38
    合并
    0.38
     synergy
    0.38
    醗
    0.37
     synergies
    0.37
    肌
    0.37
    molecule
    0.36
     ancol
    0.36
    POSITIVE LOGITS
    combe
    0.42
     Lincoln
    0.41
     కె
    0.41
     Regist
    0.39
    mith
    0.39
     Linz
    0.39
     Mist
    0.38
     Imperial
    0.38
    ronom
    0.38
    βολ
    0.37
    Activations Density 0.013%

    No Known Activations