© 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. 12466
    Prev
    Next
    INDEX
    Explanations

    the word "combination".

    oai_token-act-pair · gemini-2.0-flash

    combination

    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
     combination
    -2.27
    combination
    -2.17
     Combination
    -2.13
    Combination
    -2.03
     combinations
    -1.88
     combinatie
    -1.80
     Combinations
    -1.70
     Kombination
    -1.70
     combinación
    -1.65
     combo
    -1.60
    POSITIVE LOGITS
    WithIOException
    0.56
     LCCN
    0.51
    onAttach
    0.46
     of
    0.46
     the
    0.45
     Mor
    0.43
     VIAF
    0.43
     joined
    0.42
    폭
    0.40
     and
    0.40
    Activations Density 0.994%

    No Known Activations