© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107147
    Prev
    Next
    INDEX
    Explanations

    skilled professions or roles

    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_2_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
    ä
    1.80
    ون
    1.29
    లు
    1.13
    मध्ये
    1.11
    ف
    1.07
    ό
    1.07
    रा
    1.06
    ید
    1.05
    मधील
    1.04
    ри
    1.02
    POSITIVE LOGITS
     a
    1.45
    on
    1.27
    o
    1.24
    u
    1.05
    的相关
    0.88
    的核心
    0.86
    as
    0.83
    の間
    0.81
    のうち
    0.81
    lectual
    0.80
    Activations Density 0.001%

    No Known Activations