© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44857
    Prev
    Next
    INDEX
    Explanations

    philosophers (Kant, Rand, Marx, Arendt)

    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_22_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
     nossos
    0.44
     Approx
    0.44
    AFD
    0.42
     terrazzo
    0.42
     Хар
    0.42
     العزيز
    0.42
     большинства
    0.42
    {}".
    0.41
    енти
    0.41
     வால்பேப்ப
    0.41
    POSITIVE LOGITS
    iril
    0.39
     Education
    0.39
    ähl
    0.38
     Tu
    0.37
    </u>
    0.36
     Gita
    0.36
     influ
    0.36
     Communication
    0.36
     সহজাত
    0.35
     Development
    0.35
    Activations Density 0.001%

    No Known Activations