© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33712
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Scaffold
    0.41
     cier
    0.38
     Anterior
    0.38
     scaffold
    0.37
     '//
    0.37
     À
    0.36
     Pedersen
    0.36
     Lastly
    0.35
     পিঁপ
    0.35
     Przed
    0.35
    POSITIVE LOGITS
    になると
    0.46
    Lazy
    0.43
    䣫
    0.39
    に適
    0.39
     휘
    0.39
    ज्ञात
    0.38
     সম্মত
    0.38
    LoggedIn
    0.38
    Regex
    0.37
    Jobs
    0.37
    Activations Density 0.000%

    No Known Activations