© 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. 7458
    Prev
    Next
    INDEX
    Explanations

    words related to outcomes and procedures

    oai_token-act-pair · gemini-2.0-flash

    phrases related to querying data

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

    yielding results

    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
     yielding
    -1.47
     producing
    -1.47
     yield
    -1.38
     produce
    -1.38
     produces
    -1.33
    yield
    -1.32
     yields
    -1.27
    yielding
    -1.26
     yielded
    -1.26
     Producing
    -1.23
    POSITIVE LOGITS
     مرئيه
    0.75
     AssemblyTitle
    0.72
     مشين
    0.57
     bezeichneter
    0.56
     DBNull
    0.54
     étoit
    0.54
    bouncycastle
    0.54
    ✨:
    0.52
    cjonal
    0.52
    rature
    0.51
    Activations Density 2.515%

    No Known Activations