© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13537
    Prev
    Next
    INDEX
    Explanations

    a combination of pronouns and auxiliary verbs in the context of user preferences or experiences

    oai_token-act-pair · gemini-2.0-flash

    HTML typography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    </b>
    -3.22
    </i>
    -2.97
    <b>
    -2.41
    <i>
    -2.17
    dfrac
    -1.80
     + 
    -1.39
    </td>
    -1.35
    例文帳に追加
    -1.32
     ± 
    -1.26
     × 
    -1.23
    POSITIVE LOGITS
    </strong>
    2.16
    </em>
    2.00
     fi
    1.15
     fl
    1.05
     first
    1.00
    <em>
    0.97
     
    0.92
    fl
    0.89
    fi
    0.88
    <strong>
    0.87
    Activations Density 2.758%

    No Known Activations