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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4493
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words, with no clear throughline or pattern.

    oai_token-act-pair · gemini-2.0-flash

    the word "many" or its translations

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

    many

    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
     cref
    -0.60
    )]);
    -0.49
    %");
    -0.49
    EventQueue
    -0.47
    éndolo
    -0.46
    ofType
    -0.46
    theless
    -0.45
    rungsseite
    -0.45
    éndole
    -0.44
    UpDown
    -0.44
    POSITIVE LOGITS
     many
    3.11
    many
    2.70
    Many
    2.44
     muchos
    2.42
     Many
    2.42
     muitos
    2.39
     MANY
    2.34
     molti
    2.17
     viele
    2.11
     многие
    2.11
    Activations Density 5.019%

    No Known Activations