© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15675
    Prev
    Next
    INDEX
    Explanations

    the phrase "Deep State"

    oai_token-act-pair · gemini-2.0-flash

    Deep

    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
     Deep
    -0.75
     deep
    -0.73
    Deep
    -0.70
     DEEP
    -0.69
     deepest
    -0.69
     kasarigan
    -0.69
    deep
    -0.66
    DEEP
    -0.65
     برانيه
    -0.63
     deeper
    -0.61
    POSITIVE LOGITS
    stdc
    0.65
    GOTREF
    0.60
    béco
    0.59
    一来
    0.51
     Grandmother
    0.45
     Cardoso
    0.45
     courriel
    0.45
     Rosenberg
    0.45
    )].
    0.45
    jamientos
    0.45
    Activations Density 1.915%

    No Known Activations