© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12410
    Prev
    Next
    INDEX
    Explanations

    description phrases of states of change

    oai_token-act-pair · gemini-2.0-flash

    personal transformation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Audiodateien
    -0.70
     féminine
    -0.69
     étrangère
    -0.67
     réglable
    -0.67
     financière
    -0.66
     asiatique
    -0.66
     étrangères
    -0.65
    rítica
    -0.64
    addPreferredGap
    -0.64
     métallique
    -0.64
    POSITIVE LOGITS
    WebVitals
    0.57
     is
    0.47
    XmlEnum
    0.45
    íí
    0.44
     that
    0.43
    MigrationBuilder
    0.42
    eri
    0.41
     luật
    0.41
    NUMX
    0.39
     חוק
    0.39
    Activations Density 3.097%

    No Known Activations