© 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. 387
    Prev
    Next
    INDEX
    Explanations

    words related to electronics packaging, especially chip-on-board

    oai_token-act-pair · gemini-2.0-flash

    semiconductor wiring boards

    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
     defaultstate
    -1.02
    BeginContext
    -1.00
    awtextra
    -0.90
    SequentialGroup
    -0.84
     Roskov
    -0.82
    تقاوى
    -0.82
    LookAnd
    -0.81
     mergeFrom
    -0.79
    AccessorTable
    -0.77
    writeFieldEnd
    -0.77
    POSITIVE LOGITS
    ://
    0.47
     her
    0.45
     laikā
    0.44
    УДК
    0.40
    árl
    0.40
     hennes
    0.39
     palvel
    0.38
     hydrostatic
    0.38
     bēr
    0.38
    bidity
    0.37
    Activations Density 2.360%

    No Known Activations