© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10412
    Prev
    Next
    INDEX
    Explanations

    mathematical values and operators

    oai_token-act-pair · gemini-2.0-flash

    complex or technical terms and symbols

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

    numbers and calculations

    np_max-act-logits · gemini-2.0-flash

    ▁

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Datuak
    -0.79
    BeginContext
    -0.75
    providedIn
    -0.73
    featureID
    -0.72
     createSlice
    -0.68
     Signalez
    -0.66
     насељу
    -0.64
    adaptiveStyles
    -0.64
     bezeichneter
    -0.63
    UnsafeEnabled
    -0.62
    POSITIVE LOGITS
    %")
    0.49
     Erasmus
    0.45
    didReceive
    0.44
     Thursday
    0.43
    ínico
    0.42
    onedDateTime
    0.41
    ragalactic
    0.40
    Thursday
    0.40
    tidaknya
    0.39
     lære
    0.39
    Activations Density 1.593%

    No Known Activations