© 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. 14098
    Prev
    Next
    INDEX
    Explanations

    territorial claims and annexations

    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
    nés
    0.54
    noscript
    0.53
    sene
    0.53
     Brings
    0.53
     🤔
    0.53
    Sk
    0.52
    nels
    0.52
    après
    0.50
    Perc
    0.50
    Brasil
    0.50
    POSITIVE LOGITS
     reserva
    0.57
    ल
    0.52
     classroom
    0.45
    II
    0.45
    ิ
    0.45
    ีน
    0.44
     biển
    0.43
    ian
    0.43
     объект
    0.42
     extremo
    0.42
    Activations Density 0.029%

    No Known Activations