© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6860
    Prev
    Next
    INDEX
    Explanations

    phrases related to shopping, buying, and wanting to acquire things

    oai_token-act-pair · gemini-2.0-flash

    wanting something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Roskov
    -1.05
    principalColumn
    -0.97
     صوتيه
    -0.90
    FieldBuilder
    -0.89
     pleaſure
    -0.88
    ArrowToggle
    -0.88
    OGND
    -0.85
    sizeCache
    -0.85
    RegressionTest
    -0.84
    ANTLR
    -0.84
    POSITIVE LOGITS
     a
    0.84
     another
    0.53
     an
    0.50
     new
    0.46
     such
    0.46
     Con
    0.42
     The
    0.42
     Mus
    0.42
     
    0.41
     two
    0.41
    Activations Density 2.015%

    No Known Activations