© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2076
    Prev
    Next
    INDEX
    Explanations

    references to numerical data, especially those with specific formatting (such as dates and times)

    oai_token-act-pair · gemini-2.0-flash

    numerical values and time-related terms

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

    0

    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
    InvalidProtocol
    -0.75
    Erreferentziak
    -0.74
    eseorang
    -0.72
    MethodManager
    -0.72
    Hozzáférés
    -0.70
    ⓧ
    -0.69
    :+:
    -0.69
    outchouc
    -0.68
    AutoresizingMask
    -0.68
    onOptions
    -0.66
    POSITIVE LOGITS
    ns
    0.51
    th
    0.46
     Años
    0.43
     year
    0.41
    mas
    0.41
     Wakil
    0.41
    2
    0.41
    FT
    0.40
    ans
    0.40
     Years
    0.39
    Activations Density 7.968%

    No Known Activations