© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7207
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express a comparison, a connection, or a verification.

    oai_token-act-pair · gemini-2.0-flash

    states something is true

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ########.
    -0.74
    TestingModule
    -0.73
    +#+#
    -0.66
    .
    -0.65
    ;
    -0.63
    sidemargin
    -0.61
    WebVitals
    -0.59
    httphttps
    -0.56
    ManagedBean
    -0.56
    Климат
    -0.56
    POSITIVE LOGITS
    <bos>
    1.04
    цездатний
    0.64
    PositiveButton
    0.60
     relève
    0.53
     pasada
    0.51
    AddHtmlAttribute
    0.49
    OrBuilder
    0.49
     passada
    0.48
     elsewhere
    0.47
     manqué
    0.47
    Activations Density 12.067%

    No Known Activations