© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3783
    Prev
    Next
    INDEX
    Explanations

    the words "or", "of", and "that".

    oai_token-act-pair · gemini-2.0-flash

    related to another

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Efq
    -2.00
     myſelf
    -1.84
     ―――――
    -1.77
     itſelf
    -1.73
     Jefus
    -1.73
    AndEndTag
    -1.70
     Theſe
    -1.70
     doubtnut
    -1.70
     ་་
    -1.69
     Shakspeare
    -1.66
    POSITIVE LOGITS
     
    0.93
    ,
    0.86
     O
    0.85
    ↵
    0.84
     and
    0.83
     a
    0.79
     the
    0.78
    ↵↵
    0.78
    <eos>
    0.77
     A
    0.77
    Activations Density 15.649%

    No Known Activations