© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12824
    Prev
    Next
    INDEX
    Explanations

    technical concepts such as coding languages, APIs, SEO, plugins, and code migration

    oai_token-act-pair · gemini-2.0-flash

    Programming and web snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <bos>
    -0.68
    UpInside
    -0.57
    TagMode
    -0.47
    Portale
    -0.46
    webgl
    -0.46
    breos
    -0.46
     Nop
    -0.45
    CGRectMake
    -0.45
    enumi
    -0.45
     bezeichneter
    -0.44
    POSITIVE LOGITS
     transférez
    0.65
    forChild
    0.59
     AppCompatTheme
    0.59
     مرئيه
    0.58
     vouloir
    0.57
     legyen
    0.57
    最快更新
    0.57
     pungkasnya
    0.55
    Bronnen
    0.53
    ImageField
    0.53
    Activations Density 43.460%

    No Known Activations