© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12948
    Prev
    Next
    INDEX
    Explanations

    road and interstate designations

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     NDEBUG
    -0.78
    ">:
    -0.63
     gdyby
    -0.59
    orteur
    -0.59
     Jinping
    -0.59
    ضع
    -0.59
    INSEE
    -0.58
    limus
    -0.57
     depositphotos
    -0.57
    amerikanischer
    -0.56
    POSITIVE LOGITS
    SpringBootTest
    0.64
    +:+
    0.60
     ivi
    0.53
    protoimpl
    0.53
    SourceChecksum
    0.52
    tvguidetime
    0.49
     kasarigan
    0.48
    Rüyada
    0.47
     AssemblyCulture
    0.47
     Roskov
    0.47
    Activations Density 1.892%

    No Known Activations