© 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. 5939
    Prev
    Next
    INDEX
    Explanations

    location and preposition phrases

    oai_token-act-pair · gemini-2.0-flash

    Facilities/Workplaces

    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
     hospitals
    -1.05
     studios
    -1.01
     restaurant
    -0.98
     STORE
    -0.98
     laboratories
    -0.98
     studio
    -0.98
     store
    -0.97
     clinics
    -0.94
     offices
    -0.93
     clinic
    -0.93
    POSITIVE LOGITS
    脚注の使い方
    0.65
    GraphicsUnit
    0.49
     prénom
    0.44
     panoramique
    0.44
    WTS
    0.43
    Scénario
    0.41
    Fuckin
    0.41
     cref
    0.40
    VersionUID
    0.39
     holz
    0.38
    Activations Density 1.028%

    No Known Activations