© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153151
    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_23_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
    Distributed
    0.43
    लर
    0.42
    妛
    0.39
     preva
    0.38
     дорогие
    0.37
     announc
    0.37
     persuade
    0.37
    Rash
    0.37
     plr
    0.36
     estavam
    0.36
    POSITIVE LOGITS
     lắp
    0.42
     thérapeutique
    0.42
     ට
    0.41
    мимо
    0.41
    atschapp
    0.41
    łego
    0.41
    uraea
    0.41
    irà
    0.40
    ;\
    0.39
    enschappen
    0.39
    Activations Density 0.000%

    No Known Activations