© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8706
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to electronic engineering, manufacturing, or technical components, along with design features or specifications.

    oai_token-act-pair · gemini-2.0-flash

    dashes or slashes

    np_max-act-logits · gemini-2.0-flash

    -

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Référence
    -0.55
    usermodel
    -0.54
     htons
    -0.54
     ComVisible
    -0.51
     BorderRadius
    -0.50
    AllAfrica
    -0.48
    什么事
    -0.47
     Parcelable
    -0.45
    Interests
    -0.44
    ISPR
    -0.44
    POSITIVE LOGITS
    zipped
    0.56
    rippa
    0.55
    unzi
    0.50
    stit
    0.50
    zi
    0.49
    shank
    0.49
    errHandler
    0.49
    swatch
    0.49
    windowFixed
    0.49
    aterina
    0.48
    Activations Density 12.248%

    No Known Activations