© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4055
    Prev
    Next
    INDEX
    Explanations

    code snippets, file paths and URLs

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    UTRAL
    -0.79
    PARATOR
    -0.76
    FTFY
    -0.69
    OOTDTY
    -0.69
     Par
    -0.69
    ± 
    -0.68
    ATEGY
    -0.67
    حياته
    -0.66
    desertcart
    -0.66
    BACA
    -0.65
    POSITIVE LOGITS
    i
    0.71
     itſelf
    0.69
     moschino
    0.67
     picioare
    0.66
     bershka
    0.65
    e
    0.64
     armani
    0.63
    get
    0.63
     Rtl
    0.63
    ex
    0.61
    Activations Density 11.078%

    No Known Activations