© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177607
    Prev
    Next
    INDEX
    Explanations

    Germany

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    iste
    0.45
    ipe
    0.43
    isted
    0.41
    lika
    0.41
    <unused51>
    0.41
     Thorpe
    0.40
    lipidemia
    0.40
    IPE
    0.39
     jist
    0.37
    ienti
    0.37
    POSITIVE LOGITS
     electronics
    0.40
    wander
    0.38
     elec
    0.38
     وق
    0.38
     zaken
    0.38
    verg
    0.37
    وْ
    0.37
    ungs
    0.36
    ુક
    0.36
     Kettle
    0.36
    Activations Density 0.005%

    No Known Activations