© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1940
    Prev
    Next
    INDEX
    Explanations

    parenthesis, hyphens, numbers, and miscellaneous characters within scientific laboratory experiment texts

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    </h5>
    -1.48
    </h4>
    -1.35
    </u>
    -1.26
    </h6>
    -1.20
    }*/
    -1.20
     */
    -1.18
     */}
    -1.15
    ";}
    -1.14
    </h1>
    -1.13
    </sup>
    -1.13
    POSITIVE LOGITS
     Wikimedijinoj
    0.67
     Савезне
    0.63
     ویکی‌پدیای
    0.61
     feroit
    0.60
     otomatig
    0.58
     avoient
    0.58
    脚注の使い方
    0.57
     auroit
    0.55
    UnusedPrivate
    0.55
     vnnd
    0.54
    Activations Density 4.711%

    No Known Activations