© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16446
    Prev
    Next
    INDEX
    Explanations

    hobbies and interests

    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_34_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
     organisational
    0.42
    䧉
    0.38
    जरी
    0.38
    놔
    0.36
    Symbol
    0.36
    పం
    0.36
    ರೆಯ
    0.35
     $\%
    0.35
    秽
    0.35
    وبر
    0.35
    POSITIVE LOGITS
     hobbies
    1.27
     hobby
    1.22
    Hobbies
    1.12
    hobby
    1.10
     Hobby
    1.01
    爱好
    0.88
     interests
    0.88
    趣味
    0.84
    interests
    0.83
     interessi
    0.82
    Activations Density 0.167%

    No Known Activations