© 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. 3037
    Prev
    Next
    INDEX
    Explanations

    technical texts about a mechanical process

    oai_token-act-pair · gemini-2.0-flash

    Manufacturing/industrial processes

    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
    Espèce
    -0.64
    AddTagHelper
    -0.58
    ModelAttribute
    -0.55
    Skocz
    -0.55
    CreateModel
    -0.54
    ربای
    -0.54
    isContained
    -0.52
    requireNonNull
    -0.51
    ofire
    -0.50
     الفلك
    -0.49
    POSITIVE LOGITS
    Демографія
    0.54
     aussch
    0.52
     grids
    0.51
     '\\;'
    0.51
    lamide
    0.51
    digheid
    0.50
     Grid
    0.49
    \{\\
    0.47
     IMPLIED
    0.46
     pun
    0.46
    Activations Density 3.546%

    No Known Activations