© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4781
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies

    oai_token-act-pair · gemini-2.0-flash

    Stars and shot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     falt
    -0.61
     naselje
    -0.59
    k
    -0.58
    s
    -0.57
    No
    -0.57
    asse
    -0.55
    e
    -0.54
    te
    -0.54
     
    -0.53
    pezi
    -0.52
    POSITIVE LOGITS
    !")
    0.93
     Efq
    0.89
     Diſ
    0.89
    ^(@)
    0.86
     ſta
    0.85
    .";
    0.85
    ſelf
    0.84
     Eſ
    0.84
     ſche
    0.84
     ſhe
    0.84
    Activations Density 1.459%

    No Known Activations