© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218268
    Prev
    Next
    INDEX
    Explanations

    s

    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_47_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
     behind
    0.55
     Behind
    0.50
    Behind
    0.49
    behind
    0.47
     felicidad
    0.43
     dietro
    0.43
     뒤
    0.42
     hinter
    0.41
     Hinter
    0.41
     مستقبل
    0.41
    POSITIVE LOGITS
    大量
    0.37
    チェア
    0.37
    ﮩ
    0.37
    Hoist
    0.35
     굉장
    0.35
    ద్
    0.35
     enormes
    0.34
    糟糕
    0.34
    能源
    0.33
     strangely
    0.33
    Activations Density 0.008%

    No Known Activations