© 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. 12338
    Prev
    Next
    INDEX
    Explanations

    the letters "ct" or the letter "x" in a software, chemistry, or medical context

    oai_token-act-pair · gemini-2.0-flash

    ct

    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
     androidx
    -0.56
    androidx
    -0.54
     om
    -0.53
    sizeCache
    -0.49
    LikeLike
    -0.48
    mappedBy
    -0.47
    om
    -0.45
     
    -0.45
     "}";
    -0.44
    zyms
    -0.43
    POSITIVE LOGITS
     Efq
    0.97
    httphttps
    0.80
    okk
    0.75
     Majefty
    0.74
     "..\..\
    0.72
     ainfi
    0.71
    aquin
    0.71
     Utilizamos
    0.71
     Oc
    0.71
    OKA
    0.70
    Activations Density 0.421%

    No Known Activations