© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8677
    Prev
    Next
    INDEX
    Explanations

    words and punctuation surrounding a point of view or specific comparison

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     otomatig
    -0.86
    numerusform
    -0.79
     myſelf
    -0.75
    IBarButtonItem
    -0.70
    ſelves
    -0.70
     itſelf
    -0.70
    Билгалдахарш
    -0.68
    SequentialGroup
    -0.68
    WriteTagHelper
    -0.68
     FMI
    -0.68
    POSITIVE LOGITS
     <
    0.45
     Page
    0.41
    日閲覧
    0.41
     we
    0.40
     словарь
    0.40
     pousse
    0.39
    ándola
    0.39
     tự
    0.38
    Schriften
    0.38
     TextStyle
    0.37
    Activations Density 0.731%

    No Known Activations