© 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. 7917
    Prev
    Next
    INDEX
    Explanations

    backslash characters at the end of lines of code

    oai_token-act-pair · gemini-2.0-flash

    programming symbols and multi-language terms

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

    code and math

    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
    httphttps
    -0.60
     rowspan
    -0.52
    tonsoft
    -0.51
    licula
    -0.50
    tagHelperRunner
    -0.50
    )];
    -0.50
    DbHelper
    -0.50
    %@",
    -0.50
    Obrázky
    -0.49
     Pflicht
    -0.48
    POSITIVE LOGITS
     étudi
    0.50
    ないし
    0.49
     bezeichneter
    0.48
     voluto
    0.46
     estudia
    0.46
    InputBorder
    0.46
    PreferredItem
    0.45
     >=",
    0.45
     Startseite
    0.45
    TargetException
    0.45
    Activations Density 0.023%

    No Known Activations