© 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. 15119
    Prev
    Next
    INDEX
    Explanations

    the word "yours."

    oai_token-act-pair · gemini-2.0-flash

    yours

    np_max-act · gemini-2.0-flash

    yours

    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
    ↵↵
    -1.24
     
    -1.21
    ↵
    -1.04
    -
    -0.97
     (
    -0.96
    <eos>
    -0.91
    n
    -0.84
    .
    -0.81
     :
    -0.81
    r
    -0.80
    POSITIVE LOGITS
     Efq
    1.72
     myſelf
    1.67
     étoit
    1.66
     Monfieur
    1.65
     avoient
    1.65
     feroit
    1.63
    ^(@)
    1.62
     Jefus
    1.60
     Anſ
    1.57
    ſelf
    1.55
    Activations Density 4.021%

    No Known Activations