© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1470
    Prev
    Next
    INDEX
    Explanations

    HTML code

    oai_token-act-pair · gemini-2.0-flash

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     da
    -0.47
    通
    -0.46
     Da
    -0.45
    burg
    -0.44
     
    -0.44
     ground
    -0.43
     u
    -0.43
    (**
    -0.43
     secret
    -0.41
     pa
    -0.41
    POSITIVE LOGITS
     Efq
    0.71
     $_"
    0.71
     cdti
    0.71
    =$?
    0.68
     snippetHide
    0.68
    SpringRunner
    0.68
     auffi
    0.66
     صوتيه
    0.66
     exercí
    0.66
    ſelf
    0.66
    Activations Density 2.255%

    No Known Activations