© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6444
    Prev
    Next
    INDEX
    Explanations

    words related to user input, requests and processes

    oai_token-act-pair · gemini-2.0-flash

    terms related to approval processes and system management

    np_token-act-pair-logits · gpt-4o-mini

    asking for advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     onCancelled
    -0.56
     estekak
    -0.54
     judicia
    -0.53
     judiciales
    -0.50
     judiciaire
    -0.50
    Hozzáférés
    -0.47
     Pozn
    -0.47
     виправивши
    -0.45
     الحره
    -0.45
     Crypt
    -0.45
    POSITIVE LOGITS
     Савезне
    0.74
    DockStyle
    0.71
    <bos>
    0.70
     بيها
    0.65
    +:+
    0.63
    ArrowToggle
    0.62
    stateProvider
    0.61
    úrate
    0.59
     the
    0.59
    WebElementEntity
    0.58
    Activations Density 8.261%

    No Known Activations