© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156815
    Prev
    Next
    INDEX
    Explanations

    rudely demanding

    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_2_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
    k
    1.38
    ın
    1.27
    ן
    1.27
    ↵
    1.18
    kowe
    1.12
    el
    0.99
    ků
    0.94
    kate
    0.94
    kere
    0.94
    geteilt
    0.93
    POSITIVE LOGITS
    1.18
     be
    1.13
    ва
    1.06
     reorgan
    1.03
     responde
    1.02
     pressur
    1.01
    就
    0.98
     hypothes
    0.94
     categor
    0.93
     constru
    0.93
    Activations Density 0.001%

    No Known Activations