© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14938
    Prev
    Next
    INDEX
    Explanations

    authentication and passwords

    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
     влади
    0.45
     trafic
    0.43
    朗
    0.37
    водство
    0.37
     tund
    0.36
     trafik
    0.36
     humidity
    0.36
     lak
    0.36
     ҳу
    0.36
     opposit
    0.36
    POSITIVE LOGITS
    덴
    0.41
     متعلقه
    0.37
    𝐱
    0.37
    鉢
    0.37
     फायर
    0.36
    Race
    0.36
     Ela
    0.36
    Protected
    0.35
     protected
    0.35
     volunteer
    0.34
    Activations Density 0.001%

    No Known Activations