© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165517
    Prev
    Next
    INDEX
    Explanations

    education and technology

    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_31_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
    霊
    0.43
    खेल
    0.41
    AsyncKeyState
    0.37
    Uninstall
    0.37
    Online
    0.37
     शाळे
    0.36
    DOE
    0.36
    Energy
    0.36
    住房
    0.36
    ズニー
    0.36
    POSITIVE LOGITS
     calculation
    0.40
    月
    0.40
     pebb
    0.38
     service
    0.38
     projection
    0.38
     subscribe
    0.38
     quo
    0.38
     services
    0.38
     praw
    0.38
     diffusion
    0.38
    Activations Density 0.030%

    No Known Activations