© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137579
    Prev
    Next
    INDEX
    Explanations

    loss aversion and framing effect

    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_12_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
     العراق
    0.50
    เพราะ
    0.44
    াজন
    0.44
     i
    0.43
    ;//
    0.43
    assumption
    0.43
     interpreters
    0.42
    ひとり
    0.42
    neigh
    0.42
    inando
    0.42
    POSITIVE LOGITS
    з
    0.45
    爫
    0.42
     Dole
    0.41
    zed
    0.41
     adheres
    0.41
    𝗋
    0.40
     vessie
    0.40
    мся
    0.40
    мули
    0.39
     Tuscan
    0.39
    Activations Density 0.008%

    No Known Activations