© 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. 8732
    Prev
    Next
    INDEX
    Explanations

    code

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     nahilalakip
    -1.05
     ujednoznacz
    -0.97
     متعلقه
    -0.92
    yntaxException
    -0.88
    parsedMessage
    -0.85
    +#+
    -0.83
     himo
    -0.82
     estekak
    -0.81
     <<<<<<<<<<<<<<
    -0.80
     تكبرها
    -0.78
    POSITIVE LOGITS
     (
    0.77
    1
    0.56
     -
    0.52
     
    0.52
    (--
    0.50
     “
    0.50
    3
    0.48
    0
    0.48
     A
    0.48
     B
    0.48
    Activations Density 9.619%

    No Known Activations