© 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. 10971
    Prev
    Next
    INDEX
    Explanations

    the string "ANT" and words with a "nose" suffix

    oai_token-act-pair · gemini-2.0-flash

    ANT

    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
    ChildScrollView
    -0.73
    RectangleBorder
    -0.73
    tagHelperRunner
    -0.73
    __":
    -0.68
    __':
    -0.61
    BASELINE
    -0.56
    MER
    -0.55
    Identyfik
    -0.54
    ReusableCell
    -0.54
     crutches
    -0.54
    POSITIVE LOGITS
    MAT
    0.73
    mat
    0.69
    mah
    0.68
    MAH
    0.67
    mano
    0.67
    blockList
    0.66
    Gön
    0.65
    #+#
    0.65
    mata
    0.64
    ma
    0.63
    Activations Density 0.225%

    No Known Activations