© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206262
    Prev
    Next
    INDEX
    Explanations

    agent learns

    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_37_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
     RIGHTS
    0.43
     dump
    0.39
     belts
    0.38
    labelledby
    0.38
    GM
    0.37
    𝘤
    0.37
     వ
    0.37
     notebook
    0.37
    льном
    0.37
    মুক্তি
    0.36
    POSITIVE LOGITS
     learns
    0.41
     learn
    0.41
     öğrend
    0.40
     یاد
    0.39
    ந்த்
    0.39
    здат
    0.39
     try
    0.38
    ╠
    0.38
     quickly
    0.38
     tries
    0.38
    Activations Density 0.007%

    No Known Activations