© 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. 7754
    Prev
    Next
    INDEX
    Explanations

    the phrase "Deep State", and other words including "deep" and "over"

    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_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
     deep
    -0.97
    Deep
    -0.93
     Deep
    -0.90
    deep
    -0.90
     deeper
    -0.88
     DEEP
    -0.85
    DEEP
    -0.81
     deeply
    -0.79
     deepest
    -0.79
    深
    -0.76
    POSITIVE LOGITS
    AndEndTag
    0.70
     gynhyrchwyd
    0.69
    SourceChecksum
    0.66
    tagHelperRunner
    0.63
     vuitton
    0.58
     autorytatywna
    0.58
    water
    0.55
     виправивши
    0.54
    béco
    0.50
     שוליים
    0.48
    Activations Density 1.710%

    No Known Activations