© 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. 11611
    Prev
    Next
    INDEX
    Explanations

    measurements related to car engine size

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or model identifiers

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

    Dimensions

    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
    adpleegd
    -0.74
    Hozzáférés
    -0.72
     JpaRepository
    -0.71
    UnsafeEnabled
    -0.70
    HtmlAttribute
    -0.67
    DockStyle
    -0.66
    bewerken
    -0.65
    脚注の使い方
    -0.65
    extAlignment
    -0.64
    Carriera
    -0.63
    POSITIVE LOGITS
    rungsseite
    0.46
    getItemId
    0.45
    urb
    0.44
     sov
    0.43
    full
    0.43
     ten
    0.43
    uket
    0.43
    tirol
    0.43
    auer
    0.42
     pi
    0.41
    Activations Density 1.097%

    No Known Activations