© 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. 8297
    Prev
    Next
    INDEX
    Explanations

    Einstein, Rothschild, physics, names

    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
    δι
    0.40
     Δ
    0.39
    Dog
    0.39
     nationwide
    0.38
     Dog
    0.38
    Command
    0.37
    ③
    0.37
    Flight
    0.36
     ≤
    0.36
     lei
    0.36
    POSITIVE LOGITS
    tou
    0.41
    swald
    0.38
     alcance
    0.36
     SOCK
    0.36
    orek
    0.35
     Меди
    0.35
    鹹
    0.35
    કોટ
    0.35
     जगा
    0.35
     medico
    0.35
    Activations Density 0.016%

    No Known Activations