© 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
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197713
    Prev
    Next
    INDEX
    Explanations

    places and travel

    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
    사와
    0.41
    irradiation
    0.39
    Bezier
    0.38
    idname
    0.38
     니
    0.38
    사는
    0.37
    captivity
    0.37
     Danilo
    0.37
    mdi
    0.37
    ექს
    0.36
    POSITIVE LOGITS
    ABB
    0.45
     ABB
    0.43
    ген
    0.40
     Kho
    0.40
    Lincoln
    0.40
     Abe
    0.39
    Kho
    0.38
    gene
    0.38
     Ген
    0.38
    蜀
    0.38
    Activations Density 0.000%

    No Known Activations