© 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. 3968
    Prev
    Next
    INDEX
    Explanations

    words relating to measurement, damage, institutions, or physical locations

    oai_token-act-pair · gemini-2.0-flash

    feet

    np_max-act · gemini-2.0-flash

    feet

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    antaranya
    -0.96
     poffe
    -0.89
    berdayakan
    -0.77
    لينكات
    -0.75
     againſt
    -0.73
     investors
    -0.72
    lewati
    -0.72
    FXMLLoader
    -0.71
     asked
    -0.71
     feet
    -0.70
    POSITIVE LOGITS
     mannequin
    0.60
    ashions
    0.59
     benefici
    0.59
     ardour
    0.54
     wierd
    0.54
     cowl
    0.54
    pherical
    0.54
     Manne
    0.53
     banc
    0.53
    Invoice
    0.51
    Activations Density 9.950%

    No Known Activations