© 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. 8772
    Prev
    Next
    INDEX
    Explanations

    words used in technical documents about experimental setups.

    oai_token-act-pair · 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
     estén
    -0.49
     deve
    -0.49
     kontin
    -0.48
     matéri
    -0.46
     caza
    -0.45
     équip
    -0.44
     conto
    -0.44
     voler
    -0.44
     suje
    -0.43
     Tactics
    -0.43
    POSITIVE LOGITS
    Filmographie
    0.93
     Efq
    0.89
     photolibrary
    0.88
     ſmall
    0.88
     pleaſure
    0.85
     perfons
    0.83
     Shakspeare
    0.83
     Majefty
    0.83
     ſeveral
    0.82
     fevere
    0.81
    Activations Density 12.568%

    No Known Activations