© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46742
    Prev
    Next
    INDEX
    Explanations

    labor theory of value

    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_13_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
     U
    0.54
     ambos
    0.54
    ว
    0.53
    ு
    0.52
    uos
    0.51
    uyendo
    0.50
    imiz
    0.50
    \
    0.50
     awarding
    0.49
     הס
    0.48
    POSITIVE LOGITS
    раў
    0.57
     Applies
    0.56
    follow
    0.54
    profits
    0.53
    𝐭
    0.51
    simplify
    0.50
     inlets
    0.50
    faithful
    0.49
    𝐎
    0.49
    concern
    0.49
    Activations Density 0.002%

    No Known Activations