© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12525
    Prev
    Next
    INDEX
    Explanations

    instances of something working or not working, and the degree to which it does

    oai_token-act-pair · gemini-2.0-flash

    work

    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
    LookAnd
    -0.80
    OGND
    -0.77
    ReusableCell
    -0.77
     صوتيه
    -0.75
    WriteTagHelper
    -0.73
     Signalez
    -0.70
     ſtate
    -0.70
     dAtA
    -0.68
     fubject
    -0.68
     Wikimedijinoj
    -0.67
    POSITIVE LOGITS
    SuspendLayout
    0.45
     مشين
    0.42
     đâu
    0.42
     for
    0.40
    wpdb
    0.39
     combineReducers
    0.39
     since
    0.39
    tvguidetime
    0.38
     ok
    0.38
     at
    0.36
    Activations Density 0.858%

    No Known Activations