© 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. 8563
    Prev
    Next
    INDEX
    Explanations

    cyrillic characters and romanization of cyrillic characters.

    oai_token-act-pair · gemini-2.0-flash

    specific programming code structures

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

    foreign languages and code

    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
    sterna
    -0.66
    ningarna
    -0.60
     those
    -0.59
    isien
    -0.58
     épaules
    -0.58
    derna
    -0.58
     Those
    -0.57
    dena
    -0.57
    those
    -0.56
    ach
    -0.56
    POSITIVE LOGITS
    IndentedString
    0.79
     kaarangay
    0.60
     فريبيس
    0.58
    apunov
    0.53
    entennial
    0.52
     Meksiku
    0.51
    Népesség
    0.51
    Географи
    0.49
    apimachinery
    0.49
     bulletins
    0.48
    Activations Density 0.221%

    No Known Activations