© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14628
    Prev
    Next
    INDEX
    Explanations

    words related to areas inside a house

    oai_token-act-pair · gemini-2.0-flash

    rooms

    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
    WithIOException
    -0.70
     utafitiHapana
    -0.59
    Managed
    -0.52
     '\\;'
    -0.52
    olish
    -0.52
     Damas
    -0.52
     Terraria
    -0.50
     Bré
    -0.49
    PreInfinity
    -0.49
    PRNewswire
    -0.49
    POSITIVE LOGITS
     room
    0.76
     area
    0.57
    room
    0.56
     defaultstate
    0.56
     Room
    0.54
     raum
    0.54
     ROOM
    0.52
    θει
    0.49
     nook
    0.48
    ruimte
    0.48
    Activations Density 0.839%

    No Known Activations