Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9680
    Prev
    Next
    INDEX
    Explanations

    common words such as articles, prepositions, and pronouns

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    XmlAccessorType
    -0.67
    ########.
    -0.64
    ROIT
    -0.64
    himovic
    -0.64
     CURIAM
    -0.59
    HasAnnotation
    -0.57
    yntaxException
    -0.50
    睐
    -0.50
     WebDriverWait
    -0.50
    StatusOK
    -0.49
    POSITIVE LOGITS
    اریخ
    0.53
     invokingState
    0.52
    CodedInputStream
    0.50
     متعلقه
    0.50
    windowFixed
    0.49
    Rhestr
    0.47
    الإنجليزية
    0.47
     wren
    0.47
     layui
    0.46
     hatchet
    0.45
    Activations Density 3.842%

    No Known Activations