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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12944
    Prev
    Next
    INDEX
    Explanations

    what appear to be fragments of words from different languages and technical contexts

    oai_token-act-pair · gemini-2.0-flash

    Random/unstructured strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     defStyleAttr
    -0.61
     biais
    -0.53
    orianCalendar
    -0.53
    #+#
    -0.52
    tschaft
    -0.52
    CppMethod
    -0.50
    IsPostBack
    -0.50
     isSet
    -0.50
    dasarkan
    -0.50
    getMenuInflater
    -0.49
    POSITIVE LOGITS
    клопе
    0.65
    Autoritní
    0.64
     Normdatei
    0.60
    хьтан
    0.57
    الحياه
    0.52
    cribed
    0.51
     مشين
    0.51
    مك
    0.50
    êmica
    0.50
     незавершена
    0.49
    Activations Density 6.008%

    No Known Activations