© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12461
    Prev
    Next
    INDEX
    Explanations

    technical or formal writing related to data processing

    oai_token-act-pair · gemini-2.0-flash

    Software standards and specifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     co
    -0.44
    qrt
    -0.44
    ธรรม
    -0.43
     saja
    -0.41
    führer
    -0.41
     Roberts
    -0.40
     ob
    -0.38
    cios
    -0.38
    prach
    -0.38
     Duncan
    -0.38
    POSITIVE LOGITS
    IntoConstraints
    1.03
     snippetHide
    0.93
     disambiguazione
    0.88
    TagMode
    0.86
     Efq
    0.85
     esternos
    0.84
     ModelExpression
    0.80
     intptr
    0.79
     itſelf
    0.76
     autorytatywna
    0.73
    Activations Density 3.947%

    No Known Activations