© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235540
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    propylene
    0.42
    Princeton
    0.39
    Mys
    0.38
    bss
    0.38
    碼
    0.37
    maßnahmen
    0.37
    dda
    0.37
    量を
    0.36
    റ്റ്‌വർ
    0.36
    getKeyCode
    0.36
    POSITIVE LOGITS
     convenient
    0.42
     conveniente
    0.42
     convenience
    0.42
     Convenient
    0.41
    ಾನ್
    0.40
     Moody
    0.40
     Convenience
    0.40
     flick
    0.39
    ं
    0.39
     conveniences
    0.39
    Activations Density 0.000%

    No Known Activations