© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9160
    Prev
    Next
    INDEX
    Explanations

    type declarations in C/C++ code

    oai_token-act-pair · gemini-2.0-flash

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     GetEnumerator
    -0.66
     bezeichneter
    -0.66
     '\\;'
    -0.66
    drawSprites
    -0.65
     InputDecoration
    -0.56
    letoe
    -0.53
     >=",
    -0.53
     cortico
    -0.52
    AndroidJUnit
    -0.51
     TextFormField
    -0.51
    POSITIVE LOGITS
    BYTE
    0.76
    byte
    0.73
     byte
    0.70
    Byte
    0.69
    UCHAR
    0.66
     Byte
    0.64
    GetBytes
    0.63
     BYTE
    0.60
    UrlResolution
    0.60
    BASEPATH
    0.59
    Activations Density 0.138%

    No Known Activations