© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14326
    Prev
    Next
    INDEX
    Explanations

    instances of the word "you" or language directly addressing the reader

    oai_token-act-pair · gemini-2.0-flash

    terms related to communication or discussion

    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
    tagHelperRunner
    -0.65
     <<<<<<<<<<<<<<
    -0.63
     balanceOf
    -0.56
    SBATCH
    -0.54
     StringField
    -0.50
     dourada
    -0.50
    IANGLES
    -0.49
    reportWebVitals
    -0.49
    funds
    -0.48
     extrinsic
    -0.48
    POSITIVE LOGITS
     talk
    0.59
    talk
    0.59
     selbst
    0.54
    multicolumn
    0.51
    ensement
    0.51
     Reach
    0.51
    amsmath
    0.51
    EndProject
    0.50
    uda
    0.50
     lå
    0.50
    Activations Density 2.688%

    No Known Activations