© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12885
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and references to working, especially to save money for school

    oai_token-act-pair · gemini-2.0-flash

    jobs and working

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    脚注の使い方
    -0.54
    bukkit
    -0.47
    Manbalar
    -0.45
     ویکی‌پدیا
    -0.45
    Cubit
    -0.44
    bloc
    -0.43
    toCharArray
    -0.42
    Witam
    -0.42
    vány
    -0.41
     prof
    -0.41
    POSITIVE LOGITS
     distanciation
    0.81
    parsedMessage
    0.69
    }))
    0.68
    })));
    0.66
     Affiliations
    0.60
    IntoConstraints
    0.60
     freel
    0.59
     onCreateView
    0.59
    iction
    0.57
     freelance
    0.57
    Activations Density 2.373%

    No Known Activations