© 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-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7098
    Prev
    Next
    INDEX
    Explanations

    text related to stairwells and stairs

    oai_token-act-pair · gemini-2.0-flash

    terms related to stairs and stairways

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

    stairs

    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
    DockStyle
    -0.53
    ⓧ
    -0.51
     jScrollPane
    -0.51
    @[+][
    -0.48
     RoutedEventArgs
    -0.47
    AddTagHelper
    -0.46
    tonsoft
    -0.45
    ГЛА
    -0.44
     sabi
    -0.44
    ménage
    -0.44
    POSITIVE LOGITS
     spindles
    0.76
     landing
    0.69
     rail
    0.68
    RAIL
    0.67
     rails
    0.66
     landings
    0.65
     RAIL
    0.64
     Rail
    0.64
     Landing
    0.63
     railing
    0.60
    Activations Density 1.144%

    No Known Activations