© 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. 12064
    Prev
    Next
    INDEX
    Explanations

    lines of code assigning hexadecimal values to a variable

    oai_token-act-pair · gemini-2.0-flash

    variables or tokens associated with 'x'

    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
     autorytatywna
    -0.74
     purpoſe
    -0.70
     reaſon
    -0.70
     Majefty
    -0.70
     ſeveral
    -0.69
     leaſt
    -0.69
     internetowa
    -0.68
     Cientí
    -0.66
     reafon
    -0.66
     poffible
    -0.65
    POSITIVE LOGITS
    x
    1.14
    xf
    0.77
    xe
    0.65
    xa
    0.65
    xd
    0.65
     x
    0.63
    xc
    0.61
    ｘ
    0.57
    xb
    0.56
    ×
    0.54
    Activations Density 2.026%

    No Known Activations