© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35368
    Prev
    Next
    INDEX
    Explanations

    North Korea, denuclearization, Brexit, scheduled departure

    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_31_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
     risky
    0.43
    izontally
    0.37
     acquisition
    0.37
    氟
    0.36
     covenant
    0.36
    acquire
    0.36
     privat
    0.36
    èves
    0.35
     dest
    0.35
     serviceable
    0.35
    POSITIVE LOGITS
    ASHINGTON
    0.38
    ंदरे
    0.38
     Pellet
    0.37
     बैठ
    0.36
     embarazada
    0.36
     unaltered
    0.35
     HILL
    0.35
     ό
    0.35
     ساعات
    0.35
     accred
    0.34
    Activations Density 0.005%

    No Known Activations