© 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. 4685
    Prev
    Next
    INDEX
    Explanations

    the word "Association."

    oai_token-act-pair · gemini-2.0-flash

    Association

    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
    <bos>
    -1.20
     Its
    -0.62
     Their
    -0.59
     &
    -0.58
    ers
    -0.55
    P
    -0.55
    '
    -0.54
    its
    -0.53
    R
    -0.53
     Along
    -0.53
    POSITIVE LOGITS
    __":
    1.00
     ſta
    0.93
    celotti
    0.88
     AssemblyVersion
    0.87
     MainAxisSize
    0.86
     BaseActivity
    0.85
    ressee
    0.84
     vixion
    0.83
     quæ
    0.81
     ſtate
    0.81
    Activations Density 1.310%

    No Known Activations