© 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. 12685
    Prev
    Next
    INDEX
    Explanations

    words related to chemical composition and amounts

    oai_token-act-pair · gemini-2.0-flash

    terms suggesting quantities or comparisons

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

    of

    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
    strdup
    -0.43
    Vol
    -0.43
    وط
    -0.41
    égek
    -0.41
    
    -0.40
    olum
    -0.40
     Paglinawan
    -0.40
    ंबर
    -0.40
     Action
    -0.38
     Vol
    -0.38
    POSITIVE LOGITS
    Datuak
    0.96
     between
    0.91
     anywhere
    0.85
     about
    0.84
    Between
    0.82
    between
    0.80
     BETWEEN
    0.80
     Between
    0.79
    anywhere
    0.76
     mellan
    0.75
    Activations Density 3.665%

    No Known Activations