© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167534
    Prev
    Next
    INDEX
    Explanations

    Total

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    未
    0.41
     Pu
    0.39
     congregations
    0.38
     its
    0.38
     collaborations
    0.37
     PU
    0.35
     ثم
    0.35
     zau
    0.35
    hü
    0.35
     Nederlandse
    0.35
    POSITIVE LOGITS
     Total
    0.39
    Total
    0.38
     totale
    0.38
    瞞
    0.37
     total
    0.37
     急
    0.37
     intention
    0.36
    ັ້ງ
    0.36
    adjustment
    0.36
    产生
    0.36
    Activations Density 0.001%

    No Known Activations