© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3654
    Prev
    Next
    INDEX
    Explanations

    code-related text such as that in code documentation

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    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
     and
    -0.44
    ,
    -0.37
     with
    -0.36
     dengan
    -0.31
     the
    -0.29
     ca
    -0.28
    чини
    -0.28
    (
    -0.28
     And
    -0.27
    ，
    -0.27
    POSITIVE LOGITS
     שוליים
    0.97
    ništvo
    0.87
    HtmlAttribute
    0.87
     AVL
    0.84
     Administrativna
    0.84
     Widgets
    0.82
     Initialise
    0.81
     Paramètres
    0.80
     Daemon
    0.80
     Renderer
    0.79
    Activations Density 9.681%

    No Known Activations