© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6302
    Prev
    Next
    INDEX
    Explanations

    legal documents or correspondence and highlights parties, claims and responses.

    oai_token-act-pair · gemini-2.0-flash

    words related to statements or declarations

    np_token-act-pair-logits · gpt-4o-mini

    Letters, memos

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     religieuse
    -0.60
     murale
    -0.56
     végétale
    -0.52
     aéreas
    -0.50
     étrangères
    -0.50
    roek
    -0.49
     Sheer
    -0.49
     hjælp
    -0.48
     doccia
    -0.48
     mengirim
    -0.48
    POSITIVE LOGITS
     describing
    0.71
     saying
    0.71
    ViewFeatures
    0.70
    AutoScale
    0.69
     stating
    0.69
    FieldBuilder
    0.69
     mentioning
    0.69
    +#+#
    0.66
    mention
    0.65
     explaining
    0.64
    Activations Density 9.294%

    No Known Activations