© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6231
    Prev
    Next
    INDEX
    Explanations

    words containing "position" or "formulation"

    oai_token-act-pair · gemini-2.0-flash

    composition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     the
    -0.47
    testcase
    -0.45
    ↵↵
    -0.45
     eszköz
    -0.44
     E
    -0.44
    Uwagi
    -0.42
     em
    -0.42
     niks
    -0.42
     mű
    -0.41
    tų
    -0.41
    POSITIVE LOGITS
     composing
    1.23
     Composition
    1.16
     compose
    1.09
     compositions
    1.08
     composition
    1.06
    Composition
    1.05
    composed
    1.05
     compos
    1.05
    Compos
    1.05
     COMPOSITION
    1.04
    Activations Density 0.407%

    No Known Activations