© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    would pay

    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
     fabricating
    0.41
    ಾಟ
    0.39
    UTONIUM
    0.38
     বঙ্গবন্ধ
    0.38
    滿足
    0.38
     আকৃষ্ট
    0.37
    軹
    0.37
     fabricate
    0.37
    ೃಹ
    0.36
    满足
    0.36
    POSITIVE LOGITS
    Organ
    0.42
    ele
    0.42
    ENTER
    0.42
    Enter
    0.42
    Organisation
    0.42
     enter
    0.39
    enter
    0.38
    ፅ
    0.38
    organisation
    0.37
     Organisation
    0.37
    Activations Density 0.001%

    No Known Activations