© 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. 138033
    Prev
    Next
    INDEX
    Explanations

    CUDA

    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
    branch
    0.40
    Mot
    0.39
    Me
    0.39
    mon
    0.38
    ंत्रिक
    0.38
    DOCKED
    0.37
    ¾
    0.37
    搖
    0.37
    Paula
    0.37
    Parl
    0.37
    POSITIVE LOGITS
     Energi
    0.45
     Energy
    0.43
     Assessments
    0.42
     espirit
    0.39
     seizure
    0.39
     Omn
    0.39
     তেলে
    0.39
     colo
    0.38
    睞
    0.38
     Willing
    0.38
    Activations Density 0.000%

    No Known Activations