© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150889
    Prev
    Next
    INDEX
    Explanations

    heard something

    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_18_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
     симво
    0.48
     США
    0.46
     –
    0.46
     **)
    0.46
     красо
    0.45
     бра
    0.44
    `)
    0.43
    with
    0.43
                
    0.43
                    
    0.42
    POSITIVE LOGITS
    ക്കണം
    0.54
     that
    0.54
     স্বরে
    0.53
    trecht
    0.52
    िलं
    0.52
    न्वयन
    0.51
     oaths
    0.51
    цыю
    0.51
    ুয়ারি
    0.50
    agory
    0.50
    Activations Density 0.001%

    No Known Activations