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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8112
    Prev
    Next
    INDEX
    Explanations

    words related to statistics, data analysis, and computer science

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ^(@)
    -0.88
     purpoſe
    -0.84
    }))
    -0.81
     Majefty
    -0.79
     ſeveral
    -0.79
    Referanser
    -0.78
     greateſt
    -0.78
    OGND
    -0.77
     houſe
    -0.77
     }}"></
    -0.75
    POSITIVE LOGITS
    <bos>
    0.81
    ↵
    0.65
    ↵↵
    0.61
    bootstrapcdn
    0.59
     A
    0.51
     
    0.51
    base
    0.49
     the
    0.48
     An
    0.48
     this
    0.47
    Activations Density 2.475%

    No Known Activations