© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13723
    Prev
    Next
    INDEX
    Explanations

    cardinal directions

    oai_token-act-pair · gemini-2.0-flash

    directions

    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
    eclared
    -0.60
    derived
    -0.54
    AnchorStyles
    -0.52
    tagext
    -0.50
    MemoryWarning
    -0.48
    bigsqcup
    -0.46
    GING
    -0.46
    navbar
    -0.46
    uação
    -0.46
    stateMutability
    -0.46
    POSITIVE LOGITS
    <bos>
    0.96
     direita
    0.68
     dreapta
    0.67
     droite
    0.65
     يتيمه
    0.65
     kanan
    0.64
    quierda
    0.63
     religieuses
    0.61
     esquerda
    0.60
     derecha
    0.60
    Activations Density 1.169%

    No Known Activations