© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11944
    Prev
    Next
    INDEX
    Explanations

    words or phrases that disprove a stated position

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    InjectAttribute
    -0.70
    <bos>
    -0.63
    Ranks
    -0.63
    titudine
    -0.61
    HostException
    -0.59
    stdc
    -0.57
     digno
    -0.51
    IInterface
    -0.50
    atility
    -0.50
    Geografia
    -0.50
    POSITIVE LOGITS
     = 
    0.69
     jsPsych
    0.66
     '{}
    0.63
    imarães
    0.62
     preterm
    0.61
    alnız
    0.61
    {}/
    0.60
     "{}
    0.60
     Harriet
    0.60
    Tikang
    0.59
    Activations Density 1.576%

    No Known Activations