© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4032
    Prev
    Next
    INDEX
    Explanations

    descriptions of real estate, especially the number of bedrooms or bathrooms

    oai_token-act-pair · gemini-2.0-flash

    Real estate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    MemoryWarning
    -0.68
    
    -0.63
    LookAnd
    -0.59
    PAIGN
    -0.59
    SourceChecksum
    -0.58
    BufferException
    -0.57
     vPvB
    -0.56
     &___
    -0.56
    AddTagHelper
    -0.55
    Geplaatst
    -0.54
    POSITIVE LOGITS
    ngrx
    0.51
    ruitt
    0.49
     battre
    0.48
     innehå
    0.48
    fjspx
    0.47
    InsertCommand
    0.46
     насељу
    0.46
     picioare
    0.45
     soins
    0.45
     initWithFrame
    0.45
    Activations Density 1.589%

    No Known Activations