© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5509
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, particularly those ending in "emia", "oli", "ase", or those containing "ogen" or "ator"

    oai_token-act-pair · gemini-2.0-flash

    emia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     NgModule
    -0.68
    }^{+\
    -0.67
     שוליים
    -0.66
    FormState
    -0.66
     ChromeDriver
    -0.66
    :+:
    -0.65
    !...
    -0.64
     FetchType
    -0.63
     Smarty
    -0.63
    vier
    -0.59
    POSITIVE LOGITS
    <bos>
    2.34
    ↵↵
    0.71
    '
    0.60
     morire
    0.58
     blanches
    0.51
    The
    0.51
    ’
    0.50
    odils
    0.50
    A
    0.47
    I
    0.46
    Activations Density 1.240%

    No Known Activations