© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6360
    Prev
    Next
    INDEX
    Explanations

    real estate listings and information.

    oai_token-act-pair · gemini-2.0-flash

    Technical documents

    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
    parsedMessage
    -0.87
    Portale
    -0.75
     виправивши
    -0.74
    elemField
    -0.71
    webElementGuid
    -0.69
    Geplaatst
    -0.69
    WebElementEntity
    -0.68
    BeginInit
    -0.67
    GEBURTSDATUM
    -0.64
    isContained
    -0.63
    POSITIVE LOGITS
    NewRow
    0.47
    bender
    0.47
     antibiotics
    0.46
     mwenye
    0.44
     gradova
    0.44
    androidx
    0.43
     antibiotic
    0.43
    ływ
    0.43
    getSystemService
    0.42
    ാൻ
    0.42
    Activations Density 3.302%

    No Known Activations