© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8127
    Prev
    Next
    INDEX
    Explanations

    the word "the" or phrases associated with "Deep State" concepts

    oai_token-act-pair · gemini-2.0-flash

    Code and documentation

    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
     Little
    -1.09
    Little
    -1.02
     Big
    -1.00
     Strong
    -0.97
     Easy
    -0.96
     Bright
    -0.96
     Low
    -0.95
     Sweet
    -0.94
     Great
    -0.94
    Big
    -0.93
    POSITIVE LOGITS
     Chant
    0.36
    aarrggbb
    0.36
    طق
    0.35
     RIAA
    0.35
     '\\;'
    0.33
    oquia
    0.32
     Jagger
    0.32
    ora
    0.31
     cmap
    0.30
    awaiter
    0.30
    Activations Density 1.053%

    No Known Activations