© 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-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1901
    Prev
    Next
    INDEX
    Explanations

    the prefix "Mc" followed by a capitalized suffix in names

    oai_token-act-pair · gemini-2.0-flash

    variations of the name "Mc"

    np_token-act-pair-logits · gpt-4o-mini

    Mc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThemeOverlay
    -0.66
    ThroughAttribute
    -0.60
    lapsingToolbar
    -0.60
    ArrowToggle
    -0.58
     cytoplas
    -0.57
    SourceChecksum
    -0.56
    AnchorTagHelper
    -0.55
    
    -0.55
     cytos
    -0.54
     дописавши
    -0.54
    POSITIVE LOGITS
    Near
    0.56
    PH
    0.52
     Allociné
    0.49
     Cand
    0.46
    Di
    0.45
    ătoare
    0.45
     Near
    0.45
    Self
    0.44
    mayın
    0.44
    lach
    0.43
    Activations Density 0.363%

    No Known Activations