© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13785
    Prev
    Next
    INDEX
    Explanations

    words or phrases within a block of text that seem to be from a non-English language.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash

    say "word continuations" Method used: 2 — because the following tokens are word continuations

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     salvación
    -0.26
    ↵
    -0.22
    C
    -0.21
    R
    -0.20
    S
    -0.20
     adopción
    -0.20
     comunión
    -0.20
    B
    -0.20
    E
    -0.20
    X
    -0.19
    POSITIVE LOGITS
     myſelf
    0.94
     itſelf
    0.85
     Monfieur
    0.85
     Efq
    0.83
     Jefus
    0.79
     ―――――
    0.79
     Theſe
    0.79
     themſelves
    0.78
     himſelf
    0.76
     ſeveral
    0.73
    Activations Density 32.748%

    No Known Activations