© 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. 3261
    Prev
    Next
    INDEX
    Explanations

    words related to real estate or architectural design

    oai_token-act-pair · gemini-2.0-flash

    architectural design

    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
    اق
    -0.46
     defaultstate
    -0.43
     B
    -0.40
     Vor
    -0.40
    ferenz
    -0.40
     Q
    -0.40
     dem
    -0.39
     j
    -0.38
     T
    -0.37
    ThroughAttribute
    -0.37
    POSITIVE LOGITS
     Normdatei
    0.96
    CloseOperation
    0.88
    __':
    0.87
    SequentialGroup
    0.85
     finishes
    0.80
     GreatSchools
    0.78
    SBATCH
    0.77
    architectural
    0.77
     touches
    0.77
     architectural
    0.77
    Activations Density 1.941%

    No Known Activations