© 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. 10891
    Prev
    Next
    INDEX
    Explanations

    the word "interpret" or "interpretation," along with related words

    oai_token-act-pair · gemini-2.0-flash

    interpret

    np_max-act · 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
     Interpretation
    -0.75
    Interpretation
    -0.70
     interpreted
    -0.70
     interpretation
    -0.69
     interpretations
    -0.69
     ouvertes
    -0.65
     interpret
    -0.65
     Interpret
    -0.65
     interprets
    -0.60
    interpretation
    -0.60
    POSITIVE LOGITS
     typelib
    0.78
    extAlignment
    0.71
     unknownFields
    0.66
    VersionUID
    0.65
    AxisAlignment
    0.64
    uxxxx
    0.64
    ResumeLayout
    0.62
    PYX
    0.58
     infinite
    0.57
     actionPerformed
    0.57
    Activations Density 0.609%

    No Known Activations