© 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. 4359
    Prev
    Next
    INDEX
    Explanations

    the start of words "Cel", "Pel" or "Zel"

    oai_token-act-pair · gemini-2.0-flash

    names with 'el' or 'cel' pattern

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

    Short names, ends in el

    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
     CreateTagHelper
    -0.99
     autorytatywna
    -0.78
    SBATCH
    -0.77
    SharedCtor
    -0.74
    ContentAsync
    -0.74
     ویکی‌پدی
    -0.71
     suivants
    -0.69
    Personensuche
    -0.69
    SourceChecksum
    -0.69
    rungsseite
    -0.68
    POSITIVE LOGITS
    nicy
    0.52
    agisse
    0.44
    side
    0.44
    loss
    0.42
    rozco
    0.40
    air
    0.40
    los
    0.40
    dos
    0.39
    last
    0.39
    Skocz
    0.39
    Activations Density 0.312%

    No Known Activations