© 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. 8075
    Prev
    Next
    INDEX
    Explanations

    words related to Russian, website URLs, and the modification of those URLs

    oai_token-act-pair · gemini-2.0-flash

    phrases in a different script or language

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

    different languages

    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
     itſelf
    -1.34
     Monfieur
    -1.27
     Efq
    -1.27
     Houſe
    -1.26
     ſeveral
    -1.25
     myſelf
    -1.25
     pleaſure
    -1.24
     purpoſe
    -1.24
     themſelves
    -1.23
     Anſ
    -1.23
    POSITIVE LOGITS
     «
    0.61
     da
    0.50
     ti
    0.49
     du
    0.48
     تص
    0.46
     hier
    0.46
     kont
    0.45
     '
    0.45
     il
    0.45
     et
    0.45
    Activations Density 1.409%

    No Known Activations