© 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. 7753
    Prev
    Next
    INDEX
    Explanations

    good / ready / doing

    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
    çons
    0.38
    㡀
    0.38
    chett
    0.37
    ISTR
    0.36
    ROWN
    0.36
    载
    0.36
     đáng
    0.35
    chent
    0.34
     ná
    0.34
     ['<%=
    0.34
    POSITIVE LOGITS
     good
    1.23
    good
    1.14
    Good
    0.95
     хоро
    0.91
    GOOD
    0.90
     gute
    0.85
    好
    0.80
     buena
    0.80
     buona
    0.79
     Good
    0.79
    Activations Density 0.121%

    No Known Activations