© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3663
    Prev
    Next
    INDEX
    Explanations

    recommendations for next steps

    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_39_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
    CSC
    0.39
    惊
    0.38
     स्वादिष्ट
    0.38
    MSFont
    0.37
     온
    0.36
     Appointment
    0.36
     सिखा
    0.35
    LETIN
    0.35
     enrolling
    0.35
     термин
    0.35
    POSITIVE LOGITS
     る
    0.43
     denars
    0.39
    लियों
    0.37
    enar
    0.37
    См
    0.36
     Luca
    0.35
    מיני
    0.35
    lje
    0.34
     Strukt
    0.34
    lach
    0.34
    Activations Density 0.089%

    No Known Activations