© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9020
    Prev
    Next
    INDEX
    Explanations

    code within a code block, perhaps C# and Java

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Common
    -0.80
     license
    -0.69
    Common
    -0.69
     common
    -0.69
     COMMON
    -0.66
    license
    -0.66
    licensed
    -0.66
     licenses
    -0.65
     licence
    -0.65
     licensed
    -0.64
    POSITIVE LOGITS
    lepiej
    0.59
    žnost
    0.59
     Administrativna
    0.55
     виправивши
    0.54
     VIDEOTAPE
    0.54
    SdkVersion
    0.54
    ModelSerializer
    0.53
    CrossRef
    0.52
    CreateModel
    0.49
    بوابة
    0.48
    Activations Density 2.157%

    No Known Activations