© 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. 8412
    Prev
    Next
    INDEX
    Explanations

    python code that defines Azure CLI commands and their parameters

    oai_token-act-pair · gemini-2.0-flash

    tokens with unique formatting or special characters

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

    Code snippets

    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
    IVEREF
    -0.68
    ProgressHUD
    -0.63
    ftagPool
    -0.60
     disambiguazione
    -0.60
    ########.
    -0.60
    writeFieldEnd
    -0.59
    DEAL
    -0.58
    PMailer
    -0.57
     resourceCulture
    -0.56
     nakalista
    -0.56
    POSITIVE LOGITS
     sienta
    0.45
    DoubleQuotes
    0.44
    UVWXYZ
    0.44
    limo
    0.42
    Funciones
    0.41
    verwijspagina
    0.41
     besluit
    0.40
    ์ตูน
    0.40
    oges
    0.40
    anti
    0.40
    Activations Density 1.223%

    No Known Activations