© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15881
    Prev
    Next
    INDEX
    Explanations

    instances of wanting or needing to do something

    oai_token-act-pair · gemini-2.0-flash

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    にほんブログ村
    -0.59
    addContainerGap
    -0.54
     endwhile
    -0.51
    RefNanny
    -0.50
    argento
    -0.49
     universale
    -0.48
    modb
    -0.48
    ]--;
    -0.47
     bílá
    -0.47
     verkar
    -0.47
    POSITIVE LOGITS
     up
    1.22
     u
    1.13
    up
    1.12
     Up
    1.03
    Up
    0.99
     amp
    0.95
    UP
    0.87
     ramp
    0.85
     UP
    0.84
    ups
    0.76
    Activations Density 1.059%

    No Known Activations