© 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. 205995
    Prev
    Next
    INDEX
    Explanations

    exhibits and projects

    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
     TSC
    0.41
    ]---
    0.40
    jski
    0.39
     lava
    0.39
    ritu
    0.38
     Illustrated
    0.38
     Trinity
    0.38
     Curved
    0.38
     trigonometric
    0.38
    ovalo
    0.38
    POSITIVE LOGITS
    ময়
    0.40
    hangman
    0.40
    numberOfRecords
    0.39
    展览
    0.39
    ുമ്പോൾ
    0.39
    eca
    0.37
    ⑸
    0.36
     Fur
    0.35
    ময়
    0.35
    RESEARCH
    0.35
    Activations Density 0.004%

    No Known Activations