© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4734
    Prev
    Next
    INDEX
    Explanations

    positive words related to starting a new home associated with "to", "up", "get" and "home"

    oai_token-act-pair · gemini-2.0-flash

    interior 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     interior
    -1.95
     Interior
    -1.94
    Interior
    -1.91
     INTERIOR
    -1.78
    interior
    -1.77
     interiors
    -1.70
    INTERIOR
    -1.46
     Interiors
    -1.45
     Exterior
    -1.39
     exterior
    -1.35
    POSITIVE LOGITS
    EndGlobalSection
    0.53
    kloped
    0.53
    伯特
    0.48
    enterOuterAlt
    0.47
    ͅ
    0.46
    Compte
    0.45
    BarStyle
    0.45
    世上
    0.45
     Paglinawan
    0.45
     assoluto
    0.44
    Activations Density 1.229%

    No Known Activations