© 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. 8704
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to organizations, studies, and reports

    oai_token-act-pair · gemini-2.0-flash

    old-fashioned words

    np_max-act-logits · gemini-2.0-flash
    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
    <bos>
    -0.43
     
    -0.41
     T
    -0.40
    .
    -0.40
     tu
    -0.36
    '
    -0.35
     Z
    -0.35
    ве
    -0.33
     t
    -0.33
     O
    -0.33
    POSITIVE LOGITS
     Monfieur
    1.61
     houſe
    1.60
     Efq
    1.60
     myſelf
    1.58
     purpoſe
    1.55
     faſt
    1.52
     itſelf
    1.50
     ſeveral
    1.47
     pleaſure
    1.47
     himſelf
    1.45
    Activations Density 29.481%

    No Known Activations