© 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. 9735
    Prev
    Next
    INDEX
    Explanations

    the word "hire"

    oai_token-act-pair · gemini-2.0-flash

    hire

    np_max-act · gemini-2.0-flash

    hire

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     “
    -1.13
     B
    -1.13
    <eos>
    -1.09
     
    -1.08
     ‘
    -1.08
     K
    -1.06
      
    -1.04
     (
    -1.03
     R
    -1.03
    ↵↵
    -1.02
    POSITIVE LOGITS
     myſelf
    2.36
     Monfieur
    2.28
     Majefty
    2.22
     Houſe
    2.16
     Reſ
    2.14
     Efq
    2.11
     Theſe
    2.09
     Anſ
    2.09
     Diſ
    2.08
     ſeveral
    2.06
    Activations Density 1.697%

    No Known Activations