© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197736
    Prev
    Next
    INDEX
    Explanations

    chat

    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_46_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
     match
    0.46
    match
    0.45
    Match
    0.44
     Match
    0.44
     Matching
    0.42
     맞
    0.41
     Matches
    0.41
    Matching
    0.41
    맞
    0.41
     matching
    0.40
    POSITIVE LOGITS
     conveniente
    0.48
     convenient
    0.45
    ุง
    0.38
    安全的
    0.38
     stretches
    0.38
    conven
    0.38
     convenience
    0.37
    REFLECTION
    0.37
    方便
    0.37
    圴
    0.36
    Activations Density 0.001%

    No Known Activations