© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216349
    Prev
    Next
    INDEX
    Explanations

    testing assertions and mockito

    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_31_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
    閆
    0.38
    रायपुर
    0.38
    AuthState
    0.38
    aird
    0.37
    PROBLE
    0.37
    方法
    0.37
    рко
    0.37
     méthodes
    0.36
     পদ্ধতিতে
    0.36
    niejszych
    0.36
    POSITIVE LOGITS
     contact
    0.42
    contact
    0.41
     망
    0.39
     контакт
    0.37
     Bank
    0.37
     College
    0.36
     машину
    0.36
    mechanism
    0.36
    위를
    0.36
     manual
    0.35
    Activations Density 0.000%

    No Known Activations