© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13057
    Prev
    Next
    INDEX
    Explanations

    negation, especially the word "nothing"

    oai_token-act-pair · gemini-2.0-flash

    nothing

    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
     My
    -0.37
    My
    -0.36
     vieilles
    -0.34
    umb
    -0.33
    if
    -0.33
    Me
    -0.32
     doté
    -0.31
    entral
    -0.31
     copertina
    -0.31
     =
    -0.31
    POSITIVE LOGITS
     Normdatei
    1.03
     nakalista
    1.01
    AsUp
    1.00
    __":
    0.94
    DoubleQuotes
    0.94
    AndEndTag
    0.93
    posedge
    0.92
    ValueStyle
    0.92
    httphttps
    0.91
     Signalez
    0.91
    Activations Density 0.432%

    No Known Activations