© 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. 12936
    Prev
    Next
    INDEX
    Explanations

    numeric data, especially measurements and references

    oai_token-act-pair · gemini-2.0-flash

    various dash or hyphen-like characters

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

    dashes

    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
    \{\\
    -1.12
     AssemblyCulture
    -1.02
    yntaxException
    -0.95
    IonicModule
    -0.94
     يتيمه
    -0.91
    󠁢
    -0.90
    enumii
    -0.89
    DockStyle
    -0.88
    :");
    -0.85
     AssemblyCompany
    -0.84
    POSITIVE LOGITS
     –
    2.11
     -
    2.09
    –
    1.95
    —
    1.77
    --
    1.73
     —
    1.62
     −
    1.58
    －
    1.50
     --
    1.49
    ―
    1.42
    Activations Density 12.737%

    No Known Activations