© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9951
    Prev
    Next
    INDEX
    Explanations

    references or indicators of multiple instances or quantities.

    oai_token-act-pair · gemini-2.0-flash

    quantities or large numbers

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

    quantities of hundreds, dozens

    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
     three
    -0.66
    three
    -0.59
    Three
    -0.57
     two
    -0.53
     trois
    -0.53
     Three
    -0.53
     four
    -0.52
     três
    -0.50
     quatre
    -0.49
    two
    -0.49
    POSITIVE LOGITS
     dozen
    1.43
     dozens
    1.25
    dozen
    1.12
     Hundreds
    1.05
     hundreds
    1.02
     dizaines
    0.99
     HUND
    0.96
    hundreds
    0.94
     centaines
    0.92
     hundred
    0.90
    Activations Density 3.073%

    No Known Activations