© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182172
    Prev
    Next
    INDEX
    Explanations

    can be seen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
     problems
    0.39
     проблемы
    0.39
     समस्याएं
    0.39
    銨
    0.38
     Patient
    0.37
     Probleme
    0.37
    かもしれませんが
    0.37
    Patient
    0.37
    ttk
    0.37
    ghi
    0.36
    POSITIVE LOGITS
     incapable
    0.41
     kū
    0.39
     unjustified
    0.39
     prosperous
    0.38
     Surely
    0.38
     ++)
    0.38
     categorically
    0.37
     алма
    0.37
     burada
    0.36
     powerless
    0.36
    Activations Density 0.007%

    No Known Activations