© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206303
    Prev
    Next
    INDEX
    Explanations

    scientific models

    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
     technique
    0.38
     sampling
    0.37
     method
    0.37
    曷
    0.37
     внимание
    0.36
    ᠬ
    0.36
    bandit
    0.36
    जीटी
    0.36
     канала
    0.35
    core
    0.35
    POSITIVE LOGITS
     резко
    0.44
     Phenomenology
    0.43
    း
    0.41
     Созда
    0.39
    Spacer
    0.39
     създа
    0.38
     exponentes
    0.38
     Stacey
    0.38
     giảm
    0.37
     ослож
    0.37
    Activations Density 0.004%

    No Known Activations