© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12295
    Prev
    Next
    INDEX
    Explanations

    the word "star" and related concepts

    oai_token-act-pair · gemini-2.0-flash

    stars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     stars
    -2.64
    stars
    -1.99
     Stars
    -1.89
    Stars
    -1.87
     estrellas
    -1.61
     star
    -1.48
     STARS
    -1.46
     estrelas
    -1.33
     étoiles
    -1.32
     звезды
    -1.17
    POSITIVE LOGITS
     }}"></
    0.84
     myſelf
    0.79
     ་་
    0.77
     springfox
    0.76
    ValueStyle
    0.76
    ruptedException
    0.75
     itſelf
    0.75
     endforeach
    0.75
    ագրություններ
    0.74
    Hochspringen
    0.73
    Activations Density 1.970%

    No Known Activations