© 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. 8409
    Prev
    Next
    INDEX
    Explanations

    code snippets and financial language

    oai_token-act-pair · gemini-2.0-flash

    Code/internet snippets

    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
    kuuta
    -0.58
     disambiguazione
    -0.57
    $_['
    -0.56
     createSlice
    -0.55
     resourceCulture
    -0.52
    DockStyle
    -0.46
     meras
    -0.45
     marqué
    -0.45
    newswire
    -0.44
    atile
    -0.44
    POSITIVE LOGITS
    +#+
    0.63
     insuffisamment
    0.59
     Ganges
    0.59
     queuing
    0.59
     begging
    0.59
     handing
    0.58
     bending
    0.56
     begged
    0.56
     handed
    0.55
    belajaran
    0.55
    Activations Density 1.187%

    No Known Activations