© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 103042
    Prev
    Next
    INDEX
    Explanations

    early childhood centres

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     MI
    0.38
     Deployment
    0.38
    ී
    0.38
     проми
    0.37
     Perak
    0.37
     rất
    0.36
    ряда
    0.36
     Hg
    0.35
    Genetic
    0.35
    ກັບ
    0.35
    POSITIVE LOGITS
    琟
    0.41
     obeyed
    0.40
     Бра
    0.40
     obeys
    0.40
    巴西
    0.40
    üsseldorf
    0.38
     obedience
    0.38
    obedience
    0.37
     बाली
    0.37
    பூ
    0.37
    Activations Density 0.001%

    No Known Activations