© 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. 10409
    Prev
    Next
    INDEX
    Explanations

    instances of "figure out," or a similar phrase

    oai_token-act-pair · gemini-2.0-flash

    commands or functions typically used in programming contexts

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

    figure

    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
     find
    -0.62
    <?>>
    -0.59
     Find
    -0.57
     tìm
    -0.57
     finding
    -0.57
    Anhalt
    -0.56
    íu
    -0.54
     check
    -0.52
    調べて
    -0.52
     trouve
    -0.51
    POSITIVE LOGITS
    +#+#
    0.76
    BeginContext
    0.62
     BorderRadius
    0.60
     ComVisible
    0.60
    DeleteBehavior
    0.59
    #+#
    0.57
     which
    0.54
     صوتيه
    0.53
    tagHelperRunner
    0.52
     CreateTagHelper
    0.52
    Activations Density 1.646%

    No Known Activations