© 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. 13490
    Prev
    Next
    INDEX
    Explanations

    the word "although"

    oai_token-act-pair · gemini-2.0-flash

    although

    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
     although
    -1.69
    although
    -1.60
     Although
    -1.30
    Although
    -1.27
     aunque
    -1.20
    aunque
    -1.16
    though
    -1.10
     quoique
    -1.09
     though
    -1.05
     albeit
    -1.01
    POSITIVE LOGITS
    ulties
    0.55
     ISNI
    0.53
    HasKey
    0.52
    DispatchToProps
    0.52
     mapStateToProps
    0.51
     AspNetCore
    0.48
    dira
    0.48
    :";
    0.48
    mögens
    0.48
     MainAxisSize
    0.48
    Activations Density 0.251%

    No Known Activations