© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11338
    Prev
    Next
    INDEX
    Explanations

    phrases involving the use of the word "be" along with some qualifiers or preceding words.

    oai_token-act-pair · gemini-2.0-flash

    actions and states

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     purpoſe
    -1.03
     pleaſure
    -0.89
     myſelf
    -0.88
     ſtate
    -0.86
     uſe
    -0.85
     reaſon
    -0.84
     ſtand
    -0.83
     Anſ
    -0.82
     themſelves
    -0.82
     cauſe
    -0.79
    POSITIVE LOGITS
     he
    0.54
     met
    0.54
     ha
    0.52
    MessageOf
    0.49
    he
    0.46
     H
    0.44
     te
    0.44
     par
    0.43
    UPDATED
    0.43
     introduced
    0.42
    Activations Density 2.268%

    No Known Activations