© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9230
    Prev
    Next
    INDEX
    Explanations

    hormones

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     Assets
    0.71
     Shawn
    0.69
     assets
    0.66
    蔚
    0.65
    úd
    0.64
     Mariupol
    0.64
     सार्थक
    0.63
    毯
    0.63
    洁
    0.63
    PACS
    0.63
    POSITIVE LOGITS
     hormone
    3.20
     hormones
    3.18
     hormonal
    2.98
     Horm
    2.92
    horm
    2.89
     Hormone
    2.83
     hormon
    2.83
     horm
    2.70
    激素
    2.27
     endocrine
    2.21
    Activations Density 0.223%

    No Known Activations