© 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. 4617
    Prev
    Next
    INDEX
    Explanations

    the word "Long" followed sometimes by other words

    oai_token-act-pair · gemini-2.0-flash

    Long

    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
    ($__
    -0.59
    cery
    -0.57
    IsContent
    -0.52
    Tämä
    -0.52
     Teller
    -0.52
    fjspx
    -0.51
     Smarty
    -0.47
    MetaType
    -0.46
    afficheront
    -0.46
     Aiken
    -0.45
    POSITIVE LOGITS
    webElement
    0.64
    ();)
    0.63
     }}"></
    0.53
    клопе
    0.52
    Datuak
    0.51
    سطس
    0.51
    abbé
    0.48
    ]<<"
    0.48
    WebVitals
    0.48
    canes
    0.47
    Activations Density 1.878%

    No Known Activations