© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146783
    Prev
    Next
    INDEX
    Explanations

    divide/root both sides

    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_18_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
    علوم
    0.38
    StubCompat
    0.36
    intă
    0.35
    紾
    0.35
    科学家
    0.35
    nullptr
    0.35
     oln
    0.35
    ollary
    0.34
     denitr
    0.34
    蒟
    0.34
    POSITIVE LOGITS
     T
    0.42
     J
    0.34
     Broadcast
    0.34
    T
    0.34
     K
    0.34
     l
    0.34
     t
    0.33
     Drives
    0.33
    B
    0.33
     Brand
    0.33
    Activations Density 0.010%

    No Known Activations