© 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. 13728
    Prev
    Next
    INDEX
    Explanations

    error codes and exceptions in software code, particularly related to web applications and browser interactions

    oai_token-act-pair · gemini-2.0-flash

    Errors

    np_max-act-logits · gemini-2.0-flash

    programming-related error messages

    np_token-act-pair-logits · gpt-4o-mini
    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
     yerine
    -0.48
    Alike
    -0.41
     prima
    -0.37
    сій
    -0.37
     uzn
    -0.36
     McCull
    -0.36
    Erstellt
    -0.35
    patra
    -0.35
     AssemblyCulture
    -0.35
    宣言
    -0.34
    POSITIVE LOGITS
    XmlAccessorType
    0.81
    ⓧ
    0.78
    VersionUID
    0.74
    enseits
    0.70
    #+#
    0.68
    BufferException
    0.68
     defStyleAttr
    0.67
    tableFuture
    0.66
     ſind
    0.66
     error
    0.65
    Activations Density 4.892%

    No Known Activations