© 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. 13264
    Prev
    Next
    INDEX
    Explanations

    the verb "come" and some related words

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating arrival or presence

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

    come

    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
     "}";
    -0.58
     numerus
    -0.52
     going
    -0.50
    znik
    -0.50
    impulan
    -0.50
     ")";
    -0.49
     $('<
    -0.49
     angenommen
    -0.48
     coming
    -0.48
     [],
    -0.48
    POSITIVE LOGITS
     with
    0.83
    Rhestr
    0.68
     pre
    0.62
    with
    0.61
     pré
    0.61
     avec
    0.59
     dengan
    0.58
     prega
    0.58
    AsUp
    0.58
    Попис
    0.57
    Activations Density 0.149%

    No Known Activations