© 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. 15653
    Prev
    Next
    INDEX
    Explanations

    the word "prepare" and its variants

    oai_token-act-pair · gemini-2.0-flash

    prepare

    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
    tvguidetime
    -1.15
    脚注の使い方
    -1.15
    
    -1.14
    AndEndTag
    -1.13
     <<<<<<<<<<<<<<
    -1.04
    NOPQRST
    -1.02
     Савезне
    -1.01
    LookAnd
    -1.00
     surla
    -1.00
    __":
    -0.99
    POSITIVE LOGITS
    <b>
    0.61
    <i>
    0.60
     a
    0.55
    a
    0.54
    da
    0.53
     both
    0.51
    </i>
    0.50
    Có
    0.50
    de
    0.50
    es
    0.50
    Activations Density 1.194%

    No Known Activations