© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16174
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of articulated arms and their functions.

    oai_token-act-pair · gemini-2.0-flash

    Physics/maths

    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
     StatelessWidget
    -0.88
    contentLoaded
    -0.79
    oredCriteria
    -0.78
    LookAnd
    -0.75
    GraphicsUnit
    -0.71
    parsedMessage
    -0.69
     defaultstate
    -0.68
    NameInMap
    -0.66
    +#+#
    -0.65
     للاسماء
    -0.65
    POSITIVE LOGITS
     Do
    0.59
     DO
    0.54
    Do
    0.53
    osus
    0.50
     rev
    0.50
    DO
    0.50
     degrees
    0.50
     links
    0.48
     degree
    0.46
     Links
    0.43
    Activations Density 4.674%

    No Known Activations