© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10658
    Prev
    Next
    INDEX
    Explanations

    code and clinical terms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ins
    -0.48
    mid
    -0.47
     жела
    -0.46
    ib
    -0.44
     behöver
    -0.44
     mid
    -0.43
     space
    -0.43
     معرف
    -0.41
     processi
    -0.41
    <?
    -0.40
    POSITIVE LOGITS
    oredCriteria
    0.93
    Personendaten
    0.84
     himo
    0.81
    LookAnd
    0.79
     estekak
    0.76
    MigrationBuilder
    0.75
     disambiguazione
    0.75
    Vidite
    0.73
    AndEndTag
    0.70
    InjectAttribute
    0.69
    Activations Density 0.813%

    No Known Activations