© 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. 12668
    Prev
    Next
    INDEX
    Explanations

    the word "Sal" or a similar word

    oai_token-act-pair · gemini-2.0-flash

    sal

    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
     Belf
    -0.50
    1
    -0.47
    File
    -0.46
    World
    -0.45
    だい
    -0.44
    класс
    -0.43
     linea
    -0.42
     World
    -0.42
    ClassLoader
    -0.42
    land
    -0.42
    POSITIVE LOGITS
    expandindo
    0.85
     للاسماء
    0.84
    intios
    0.80
    SBATCH
    0.76
    MessageTagHelper
    0.73
    IntoConstraints
    0.72
    FormTagHelper
    0.72
    jmniej
    0.69
    Datuak
    0.69
     كومونز
    0.68
    Activations Density 0.247%

    No Known Activations