© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12717
    Prev
    Next
    INDEX
    Explanations

    the letter "P" followed by a period, or the letter "P" by itself

    oai_token-act-pair · gemini-2.0-flash

    P

    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
    Jîn
    -0.59
     Inheritance
    -0.54
    GEBURTS
    -0.54
    tanleria
    -0.54
    gwt
    -0.53
     OFDb
    -0.52
    aimana
    -0.52
    cted
    -0.52
     WebApplication
    -0.52
    ishment
    -0.52
    POSITIVE LOGITS
    fahr
    0.42
    راط
    0.42
    anyan
    0.40
    ⪢
    0.40
     behö
    0.39
    empel
    0.39
    PyExc
    0.39
    atista
    0.39
     senti
    0.38
     mele
    0.38
    Activations Density 0.316%

    No Known Activations