© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 197645
    Prev
    Next
    INDEX
    Explanations

    URL separator

    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
     parois
    0.46
    mnf
    0.42
    กัด
    0.37
    强化
    0.37
    伍
    0.37
     voltar
    0.37
     Jú
    0.36
     nacht
    0.36
     Herstellung
    0.36
     কারাগারে
    0.36
    POSITIVE LOGITS
     Con
    0.51
    Con
    0.44
    amssymb
    0.44
    ப்போதும்
    0.44
    moil
    0.42
    }.$
    0.39
    paysys
    0.38
     Concord
    0.38
    breath
    0.38
     Sli
    0.37
    Activations Density 0.000%

    No Known Activations