© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198312
    Prev
    Next
    INDEX
    Explanations

    internet company

    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_46_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
    Central
    0.42
    AIDS
    0.40
     AIDS
    0.39
    णु
    0.38
    koch
    0.38
    鼍
    0.38
    Opel
    0.38
    zość
    0.38
    பாட
    0.38
    梓
    0.38
    POSITIVE LOGITS
    net
    0.44
     нему
    0.43
     Net
    0.41
     कॉंग्रेस
    0.39
     net
    0.38
    Net
    0.38
    getResource
    0.37
    लामा
    0.36
     Company
    0.36
    EndTime
    0.36
    Activations Density 0.020%

    No Known Activations