© 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
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11464
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially grouped and formatted in tables

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Efq
    -1.20
     Theſe
    -1.14
     Jefus
    -1.12
    ſelf
    -1.11
     Reſ
    -1.09
     myſelf
    -1.07
     purpoſe
    -1.05
     itſelf
    -1.05
     Monfieur
    -1.05
     Majefty
    -1.03
    POSITIVE LOGITS
    <eos>
    0.53
     u
    0.46
     
    0.45
     «
    0.43
     U
    0.43
     “
    0.42
     t
    0.42
     "
    0.41
     The
    0.41
     A
    0.41
    Activations Density 4.137%

    No Known Activations