© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170774
    Prev
    Next
    INDEX
    Explanations

    youth

    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_56_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
     Young
    0.46
     ребенка
    0.43
    시키는
    0.41
     đứa
    0.38
     ребён
    0.38
    俬
    0.37
    Young
    0.37
    Რ
    0.37
     обо
    0.36
    ustus
    0.36
    POSITIVE LOGITS
     youth
    2.91
    Youth
    2.42
     Youth
    2.41
    youth
    2.41
     juventud
    1.83
     ungdom
    1.74
     Jugend
    1.59
     молоде
    1.55
     jeunesse
    1.52
    青年
    1.37
    Activations Density 0.012%

    No Known Activations