© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14343
    Prev
    Next
    INDEX
    Explanations

    key-value assignments

    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_34_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
     života
    0.37
     westward
    0.34
    Bret
    0.34
    LEA
    0.34
    la
    0.34
    
    0.34
     ї
    0.33
    Encom
    0.33
    </img>
    0.33
    ây
    0.33
    POSITIVE LOGITS
     guise
    0.39
     Greenhouse
    0.38
     index
    0.38
     ai
    0.38
     asymptotic
    0.38
     status
    0.37
     Ai
    0.37
     infine
    0.37
    anks
    0.36
     roya
    0.36
    Activations Density 0.064%

    No Known Activations