© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58560
    Prev
    Next
    INDEX
    Explanations

    moral or religious virtue

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    轄
    0.45
    攔
    0.40
     messages
    0.39
     legal
    0.38
     ministry
    0.38
    っかり
    0.38
     discerned
    0.37
     Prop
    0.37
     iterated
    0.37
     andando
    0.37
    POSITIVE LOGITS
    adians
    0.42
    holiday
    0.41
    Conserv
    0.39
    pedido
    0.38
    奈川
    0.38
    érieur
    0.38
    괌
    0.36
    Holiday
    0.35
    oying
    0.35
    endam
    0.35
    Activations Density 0.011%

    No Known Activations