© 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. 13218
    Prev
    Next
    INDEX
    Explanations

    instances of "should be noted" or similar phrases used to call out something within a technical document.

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating important observations or notes

    np_token-act-pair-logits · gpt-4o-mini
    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
    IndentedString
    -0.58
    ècie
    -0.57
    writeFieldEnd
    -0.57
    — 
    -0.56
    addPreferredGap
    -0.54
     cast
    -0.53
     VizieR
    -0.52
     ErrIntOverflow
    -0.52
    auteuil
    -0.51
    selaer
    -0.51
    POSITIVE LOGITS
    ImageField
    0.61
     saiba
    0.60
    enumi
    0.60
     cuillère
    0.55
     know
    0.54
     conhecido
    0.54
     linho
    0.53
     ninguém
    0.52
     nessuno
    0.52
    jenner
    0.52
    Activations Density 1.506%

    No Known Activations