© 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. 14121
    Prev
    Next
    INDEX
    Explanations

    lines of mostly whitespace or code elements, possibly related to formatting or code structure

    oai_token-act-pair · gemini-2.0-flash

    programming terms and code syntax

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

    Code/technical terms

    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
    __).
    -0.47
    hams
    -0.41
    dAtA
    -0.40
    ensement
    -0.39
     Usually
    -0.39
    lierte
    -0.37
    язы
    -0.37
    ++;
    -0.37
    baomidou
    -0.37
     tarta
    -0.36
    POSITIVE LOGITS
    RegressionTest
    0.99
     Paglinawan
    0.81
    Tikang
    0.79
    kloped
    0.74
    zzleHttp
    0.73
    Personendaten
    0.72
    IContainer
    0.72
     <=",
    0.70
    IntoConstraints
    0.69
     wikipagina
    0.68
    Activations Density 2.521%

    No Known Activations