© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14605
    Prev
    Next
    INDEX
    Explanations

    words related to construction, modification, or improvement of buildings or spaces

    oai_token-act-pair · gemini-2.0-flash

    renovations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    RUCT
    -0.46
     reten
    -0.42
     fond
    -0.40
     renovations
    -0.40
     renovation
    -0.40
     infraestructura
    -0.40
    ीन
    -0.39
    梓
    -0.39
    fic
    -0.39
    ::
    -0.38
    POSITIVE LOGITS
    ंदीखरीदारी
    1.23
    __*/
    1.06
     ComVisible
    0.99
     <=",
    0.98
     lenker
    0.91
    httphttps
    0.91
    NOPQRST
    0.86
    :✨
    0.85
    ########.
    0.84
    AddTagHelper
    0.84
    Activations Density 43.781%

    No Known Activations