© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13220
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind entities

    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_40_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
    dest
    0.39
    త్రిక
    0.38
     Ruta
    0.37
    пуск
    0.36
     کہاں
    0.35
    铉
    0.35
    芗
    0.34
     வச
    0.34
     Aktion
    0.34
    cupertino
    0.34
    POSITIVE LOGITS
    entities
    0.60
     entity
    0.57
     entities
    0.56
    Entity
    0.55
     entidade
    0.55
     Entity
    0.53
    entity
    0.51
    Entities
    0.51
     teams
    0.49
     Entities
    0.49
    Activations Density 0.102%

    No Known Activations