© 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. 12699
    Prev
    Next
    INDEX
    Explanations

    quantum gravity and electrodynamics

    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
     cutoff
    0.51
    cutoff
    0.47
    ότερα
    0.42
     রাষ্ট্রীয়
    0.41
     Cut
    0.40
    ียร์
    0.39
    婷
    0.39
    截
    0.38
     cut
    0.38
     legitimacy
    0.36
    POSITIVE LOGITS
     electro
    0.47
    odynamics
    0.44
    Turb
    0.44
     Gravity
    0.43
    turbulence
    0.43
     gravity
    0.43
    ald
    0.42
    gravity
    0.41
    Gravity
    0.41
     dinam
    0.41
    Activations Density 0.022%

    No Known Activations