© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8988
    Prev
    Next
    INDEX
    Explanations

    structured data field descriptions

    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
     riguardo
    0.39
    指令
    0.39
     রেলস্ট
    0.38
    rew
    0.38
     vär
    0.36
    읊
    0.36
    Rew
    0.36
    轟
    0.36
     rid
    0.36
     estimés
    0.35
    POSITIVE LOGITS
     fault
    0.53
    Fault
    0.47
     faulted
    0.45
     Fault
    0.44
    fault
    0.42
    ಿಸಬಹುದು
    0.39
    Fix
    0.39
    InitStruct
    0.39
     permission
    0.38
     Fix
    0.38
    Activations Density 0.162%

    No Known Activations