© 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. 9852
    Prev
    Next
    INDEX
    Explanations

    words or short phrases written in a language other than English mixed in with English

    oai_token-act-pair · gemini-2.0-flash

    words associated with coding functions or programming syntax

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

    s

    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
    ச
    -0.39
     per
    -0.37
    -
    -0.36
     +
    -0.36
     @
    -0.34
    Figure
    -0.33
    +
    -0.32
     State
    -0.32
    R
    -0.32
    .
    -0.32
    POSITIVE LOGITS
    IUrlHelper
    1.06
     Paglinawan
    0.96
     CreateTagHelper
    0.94
     nahilalakip
    0.94
     purpoſe
    0.92
    GEBURTSDATUM
    0.90
     itſelf
    0.88
    ]--;
    0.86
     Jefus
    0.85
     Efq
    0.84
    Activations Density 0.383%

    No Known Activations