© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17684
    Prev
    Next
    INDEX
    Explanations

    Watchtower Society texts

    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_40_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
    spars
    0.37
     Mona
    0.36
    Clean
    0.35
    Corner
    0.35
    र्स
    0.35
    綠
    0.35
    SetName
    0.35
     মনি
    0.34
    绿
    0.34
    ALAR
    0.34
    POSITIVE LOGITS
     Tower
    0.46
     Watch
    0.43
    Tower
    0.42
     tower
    0.42
     watchers
    0.41
     torre
    0.38
     Guardian
    0.38
    tower
    0.38
     Distributor
    0.38
     Breakthrough
    0.37
    Activations Density 0.001%

    No Known Activations