© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54133
    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_31_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
    }}},
    0.41
     따
    0.37
    이다
    0.35
     सीधा
    0.35
    cupertino
    0.35
    hasht
    0.34
    fft
    0.34
     triplets
    0.34
    0.34
    unctional
    0.33
    POSITIVE LOGITS
     Doe
    0.40
    พลาด
    0.40
     glass
    0.39
     美
    0.39
     Earle
    0.39
     আমি
    0.38
    玻璃
    0.38
    THROW
    0.37
     emptied
    0.37
     episcop
    0.37
    Activations Density 0.000%

    No Known Activations