© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10736
    Prev
    Next
    INDEX
    Explanations

    the word "withdraw" and the pronoun "him" in legal and medical documents

    oai_token-act-pair · gemini-2.0-flash

    withdraw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    +#+#
    -1.44
    WriteTagHelper
    -1.00
    writeFieldEnd
    -0.98
    ProgressHUD
    -0.92
    Portail
    -0.88
     nahilalakip
    -0.88
    omock
    -0.85
    protoimpl
    -0.85
    NewUrlParser
    -0.84
    StandardCharsets
    -0.84
    POSITIVE LOGITS
     férfi
    0.75
     jellemző
    0.71
     vectoriales
    0.71
     női
    0.69
     étanche
    0.67
     dramatique
    0.67
     vierge
    0.65
     lenger
    0.64
     megfe
    0.64
     neutre
    0.63
    Activations Density 2.368%

    No Known Activations