© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219600
    Prev
    Next
    INDEX
    Explanations

    Shadow ITMethod 1All MAX_ACTIVATING_TOKENS are variations of "Shadow"

    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
    Negative Logits
    }+(\
    0.41
     OMG
    0.40
     antiviral
    0.39
     ups
    0.37
     TTS
    0.37
     rối
    0.36
    amsmath
    0.36
    луу
    0.36
     BTS
    0.36
     соба
    0.36
    POSITIVE LOGITS
    ister
    0.41
    メール
    0.40
    istently
    0.39
    matism
    0.39
    갈
    0.38
     terj
    0.38
    remo
    0.37
     पि
    0.37
    rectomy
    0.37
    avier
    0.37
    Activations Density 0.001%

    No Known Activations