© 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. 67292
    Prev
    Next
    INDEX
    Explanations

    state

    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
     Sequence
    0.40
     Parallel
    0.40
     Neutron
    0.38
    λαν
    0.38
    edition
    0.38
    ઉન
    0.38
     сек
    0.37
    흔
    0.37
     Edition
    0.37
     edition
    0.36
    POSITIVE LOGITS
    剥
    0.42
     gifting
    0.40
     adhesions
    0.39
     popping
    0.39
     legion
    0.38
     valued
    0.38
     anticipated
    0.37
     ripping
    0.37
    exports
    0.37
     ah
    0.37
    Activations Density 0.004%

    No Known Activations