© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10584
    Prev
    Next
    INDEX
    Explanations

    the words 'so', 'far', 'to', and 'thus'

    oai_token-act-pair · gemini-2.0-flash

    Progress

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     thus
    -2.64
     so
    -2.23
    Thus
    -2.06
    thus
    -2.06
     Thus
    -2.02
    So
    -1.68
    so
    -1.66
     So
    -1.59
     así
    -1.53
     hence
    -1.48
    POSITIVE LOGITS
     '\\;'
    0.76
    InjectAttribute
    0.75
    terday
    0.65
     NSCoder
    0.63
     utafitiHapana
    0.62
     far
    0.62
     nakalista
    0.60
    NewUrlParser
    0.59
     كومونز
    0.58
     Administrativna
    0.58
    Activations Density 0.401%

    No Known Activations