© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15892
    Prev
    Next
    INDEX
    Explanations

    command prefixes

    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_34_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
     target
    0.39
     parachute
    0.38
     Harrow
    0.38
     parach
    0.37
    而已
    0.37
     Trial
    0.36
    〉
    0.35
     sky
    0.35
    Bounce
    0.35
     bounce
    0.34
    POSITIVE LOGITS
    prefix
    0.38
     '#'
    0.36
    comand
    0.36
     //#
    0.35
    腓
    0.35
    ")/
    0.35
    }.$
    0.34
     gasp
    0.34
    生长
    0.34
     "#
    0.33
    Activations Density 0.125%

    No Known Activations