© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2442
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of chemical experimental procedures and materials

    oai_token-act-pair · gemini-2.0-flash

    scientific, experimental incubation

    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
    nota
    -0.43
     bílá
    -0.41
     aguj
    -0.40
    lelő
    -0.40
     vägen
    -0.39
     devoirs
    -0.39
     volo
    -0.39
     defaultstate
    -0.39
     merve
    -0.38
    addImage
    -0.38
    POSITIVE LOGITS
    mergeFrom
    0.67
    jooq
    0.65
    AddTagHelper
    0.64
    tagHelperRunner
    0.63
    ]")]
    0.63
     "}";
    0.62
    ()][
    0.60
    AutoScaleMode
    0.60
    **/
    0.60
    )));
    0.59
    Activations Density 15.708%

    No Known Activations