© 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. 8078
    Prev
    Next
    INDEX
    Explanations

    human activities

    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
     Rho
    0.39
     rho
    0.36
    𝔯
    0.35
    Rho
    0.33
    rolyte
    0.33
    rho
    0.33
     AVL
    0.32
    брь
    0.32
    巖
    0.32
     stab
    0.32
    POSITIVE LOGITS
     human
    2.34
     humans
    2.16
    human
    2.14
    Human
    2.14
     челове
    2.09
    人类
    2.08
     인간
    2.08
     Human
    2.06
    Humans
    1.98
     manusia
    1.96
    Activations Density 0.111%

    No Known Activations