© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259863
    Prev
    Next
    INDEX
    Explanations

    maps

    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_22_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
     harboring
    0.39
    ógico
    0.38
     creativo
    0.37
     aislado
    0.37
    GISLATIVE
    0.36
    뚱
    0.36
    mería
    0.36
    ٹرول
    0.35
     creado
    0.35
     perpetrator
    0.35
    POSITIVE LOGITS
    บัน
    0.44
     fieldwork
    0.41
    р
    0.40
     charters
    0.38
     прово
    0.37
     kert
    0.37
     excellently
    0.37
     Brink
    0.37
     Se
    0.37
     batted
    0.37
    Activations Density 0.001%

    No Known Activations