© 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. 10921
    Prev
    Next
    INDEX
    Explanations

    the word "for" followed by a number

    oai_token-act-pair · gemini-2.0-flash

    words starting with "pri", "Spo", "po", "ch", "pod", "za", "le", "d"

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

    for

    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
     للمعارف
    -0.69
     الرياضيه
    -0.69
     surla
    -0.65
     Monfieur
    -0.63
     CGRectMake
    -0.62
     ſeveral
    -0.58
     poffible
    -0.58
    EndContext
    -0.57
     caufe
    -0.57
     CWE
    -0.56
    POSITIVE LOGITS
    eqn
    0.66
     pri
    0.52
    </caption>
    0.47
     Spo
    0.45
     po
    0.45
     ch
    0.45
     pod
    0.44
     za
    0.44
     le
    0.41
     d
    0.41
    Activations Density 0.357%

    No Known Activations