© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9485
    Prev
    Next
    INDEX
    Explanations

    words that are capitalized and/or related to titles

    oai_token-act-pair · gemini-2.0-flash

    possessive words

    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
     From
    -1.42
     With
    -1.37
    From
    -1.31
    With
    -1.23
     Through
    -1.20
     By
    -1.14
     Against
    -1.14
    Against
    -1.12
    Through
    -1.11
     Without
    -1.10
    POSITIVE LOGITS
     The
    0.66
     Our
    0.60
     ""],
    0.57
     Their
    0.56
     Its
    0.55
     Your
    0.51
    Our
    0.50
    Your
    0.50
     His
    0.48
     These
    0.48
    Activations Density 6.210%

    No Known Activations