© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6364
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to scientific data and mathematical models

    oai_token-act-pair · gemini-2.0-flash

    terms related to data rates and scientific measurements

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

    Scientific studies

    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
    uxxxx
    -0.88
     Shakspeare
    -0.78
    PerformLayout
    -0.73
     Shaksp
    -0.68
     Jefus
    -0.67
    ########.
    -0.66
     fubject
    -0.66
     moschino
    -0.66
     pngtree
    -0.64
     ―――――
    -0.63
    POSITIVE LOGITS
     Chwiliwch
    0.47
    Lang
    0.47
    rome
    0.46
    db
    0.45
    økt
    0.43
     lang
    0.43
    DB
    0.42
    ugu
    0.42
     second
    0.41
    次
    0.41
    Activations Density 4.879%

    No Known Activations