© 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. 1480
    Prev
    Next
    INDEX
    Explanations

    assertions or claims and evidence or support about a topic

    oai_token-act-pair · gemini-2.0-flash

    Arguments and rebuttals

    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
     Efq
    -0.77
     Jefus
    -0.64
     resourceCulture
    -0.61
     '\\;'
    -0.59
    Datuak
    -0.59
     AssemblyCompany
    -0.59
     <=",
    -0.57
     gynnwys
    -0.57
    actéristique
    -0.56
     pints
    -0.56
    POSITIVE LOGITS
    archiviato
    0.55
     me
    0.49
    ign
    0.46
    AndEndTag
    0.46
    WO
    0.45
     half
    0.45
    igned
    0.45
    WebVitals
    0.45
    Accessors
    0.45
     err
    0.45
    Activations Density 4.812%

    No Known Activations