© 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. 9131
    Prev
    Next
    INDEX
    Explanations

    analysis and analytics

    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
     Funktion
    0.19
     Functional
    0.17
    Password
    0.17
    funktion
    0.17
    Conteudos
    0.17
    ུ
    0.17
     Energy
    0.17
     чувство
    0.17
    Blueprint
    0.17
     Fun
    0.16
    POSITIVE LOGITS
    ке
    0.20
    onu
    0.19
    咨
    0.19
    ینا
    0.18
     ለእ
    0.18
    ка
    0.18
    날
    0.17
    се
    0.17
    гона
    0.17
     hemolytic
    0.17
    Activations Density 0.155%

    No Known Activations