© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10530
    Prev
    Next
    INDEX
    Explanations

    words related to historical conflicts, life and death

    oai_token-act-pair · gemini-2.0-flash

    words related to persistence or continuity

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

    continuation

    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
    Personendaten
    -0.45
    writeHead
    -0.43
     liggen
    -0.43
     العاده
    -0.42
    кало
    -0.42
     kept
    -0.41
     român
    -0.40
    Keeping
    -0.40
     iniziale
    -0.40
     élé
    -0.39
    POSITIVE LOGITS
     continues
    0.91
    continues
    0.82
     continue
    0.81
    continue
    0.81
     conti
    0.79
    conti
    0.77
     utafitiHapana
    0.76
     persists
    0.74
     Continue
    0.73
     persist
    0.71
    Activations Density 1.262%

    No Known Activations