© 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. 7803
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to time and the length/duration of something

    oai_token-act-pair · gemini-2.0-flash

    numeric representations of 'four'

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

    numbers

    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
    TypedDataSet
    -0.79
     half
    -0.71
     hour
    -0.69
    Half
    -0.65
    half
    -0.64
     Fifty
    -0.63
     Thirty
    -0.62
    DockStyle
    -0.62
     quarter
    -0.61
     GoogleFonts
    -0.60
    POSITIVE LOGITS
     four
    0.92
     Four
    0.81
     three
    0.78
    Four
    0.76
    four
    0.71
     quatre
    0.71
     quatro
    0.71
     trois
    0.70
    Three
    0.69
     cuatro
    0.68
    Activations Density 0.729%

    No Known Activations