© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12147
    Prev
    Next
    INDEX
    Explanations

    the word "had", contractions of "had", and words that often follow "had."

    oai_token-act-pair · gemini-2.0-flash

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     كومونز
    -0.98
     GenerationType
    -0.92
     виправивши
    -0.91
    verwijspagina
    -0.86
    mybatisplus
    -0.81
    Personendaten
    -0.80
     propOrder
    -0.79
     Italijanski
    -0.77
    FunctionFlags
    -0.77
     ComVisible
    -0.77
    POSITIVE LOGITS
    <bos>
    0.70
     was
    0.65
    was
    0.64
    '
    0.63
     been
    0.63
     
    0.62
    "
    0.59
    ‘
    0.57
    ’
    0.56
    </td>
    0.55
    Activations Density 0.794%

    No Known Activations