© 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. 4485
    Prev
    Next
    INDEX
    Explanations

    the word "however".

    oai_token-act-pair · gemini-2.0-flash

    however

    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
    PerformLayout
    -0.89
     however
    -0.87
    SequentialGroup
    -0.79
    حياته
    -0.79
     gainera
    -0.75
     anyway
    -0.69
     meanwhile
    -0.69
     فريبيس
    -0.68
    brigens
    -0.68
    ArgumentParser
    -0.67
    POSITIVE LOGITS
    <bos>
    1.02
    '
    0.53
    NamedQueries
    0.47
     access
    0.43
    ’
    0.43
     savent
    0.43
     rağmen
    0.43
     kandungan
    0.42
     Puoi
    0.42
    ďaka
    0.42
    Activations Density 0.782%

    No Known Activations