© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3898
    Prev
    Next
    INDEX
    Explanations

    references to governmental states, republics, or courts

    oai_token-act-pair · gemini-2.0-flash

    states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     States
    -1.96
    States
    -1.66
     states
    -1.55
     STATES
    -1.53
    states
    -1.31
    STATES
    -1.19
     estados
    -0.91
    <bos>
    -0.84
     Estados
    -0.80
    Estados
    -0.79
    POSITIVE LOGITS
    MemoryWarning
    0.55
    ernoo
    0.52
    łek
    0.52
     Picchu
    0.52
    engeance
    0.50
     Lokales
    0.49
    numerusform
    0.48
    proteins
    0.48
    spartner
    0.48
    gigi
    0.47
    Activations Density 3.633%

    No Known Activations