© 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. 1156
    Prev
    Next
    INDEX
    Explanations

    words which are parts of titles or otherwise have a certain kind of official tone

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    ſelves
    -1.31
     myſelf
    -1.27
     doubtnut
    -1.24
     ་་
    -1.24
    Portale
    -1.24
     Efq
    -1.23
     חיצוניים
    -1.22
     pleaſure
    -1.21
     itſelf
    -1.21
    ſelf
    -1.20
    POSITIVE LOGITS
     the
    0.47
     (
    0.43
     $\
    0.39
     in
    0.34
    …
    0.33
     ser
    0.32
    »
    0.32
    ?
    0.32
     
    0.32
     &
    0.32
    Activations Density 1.805%

    No Known Activations