© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10735
    Prev
    Next
    INDEX
    Explanations

    words that co-occur next to certain prepositions and nouns, like 'in the', 'spent with', or 'side by side'.

    oai_token-act-pair · gemini-2.0-flash

    experiences, time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    вз
    -0.46
    icza
    -0.44
     [
    -0.42
     Codable
    -0.40
     normal
    -0.39
     StringTokenizer
    -0.39
    rungsseite
    -0.39
    nande
    -0.39
    araus
    -0.38
     she
    -0.38
    POSITIVE LOGITS
     InputDecoration
    0.72
    bootstrapcdn
    0.72
     Houſe
    0.69
    insegna
    0.69
     houſe
    0.66
    TagHelper
    0.65
    fjspx
    0.64
    addPreferredGap
    0.61
    envolvimento
    0.61
     تضيفلها
    0.60
    Activations Density 0.884%

    No Known Activations