© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197178
    Prev
    Next
    INDEX
    Explanations

    loops and assignments

    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_27_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
     වඩා
    0.33
     inception
    0.33
    ודה
    0.33
    蟆
    0.32
    Dade
    0.32
    ত্রী
    0.32
     multiplic
    0.31
    Double
    0.31
     зна
    0.30
    뀝
    0.30
    POSITIVE LOGITS
     دسترس
    0.38
     samoch
    0.37
     sahibi
    0.36
     bày
    0.35
    四周
    0.35
     cannabis
    0.35
     सकते
    0.35
    following
    0.34
    atu
    0.34
     сервис
    0.34
    Activations Density 0.001%

    No Known Activations