Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167216
    Prev
    Next
    INDEX
    Explanations

    GetComponent

    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
     “
    0.46
     mang
    0.46
     «
    0.45
     Corpo
    0.44
     ‘
    0.41
    ÉR
    0.41
    :”
    0.41
    「
    0.40
     /
    0.40
     \"
    0.40
    POSITIVE LOGITS
     குழந்த
    0.46
    CHILD
    0.44
    child
    0.39
     ข้าง
    0.39
    குழந்த
    0.38
    子供
    0.37
     குழந்தைகள்
    0.37
     çoc
    0.37
     dziecko
    0.37
     बच्चे
    0.36
    Activations Density 0.001%

    No Known Activations