© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14622
    Prev
    Next
    INDEX
    Explanations

    words with the letters "is" and words related to magazines, succession, fantasy, communication, type/design, and evolution.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     autorytatywna
    -0.72
     uska
    -0.64
    InlineData
    -0.60
     RouterModule
    -0.60
    لينكات
    -0.59
    Autoritní
    -0.59
    toMatch
    -0.56
     TextInputType
    -0.56
    ########.
    -0.56
     jScrollPane
    -0.56
    POSITIVE LOGITS
    WindowConstants
    0.56
    QUART
    0.51
     habet
    0.49
    lapsingToolbar
    0.48
    YGON
    0.45
     này
    0.45
     OMITBAD
    0.44
    madol
    0.44
    InjectAttribute
    0.43
    ORAGE
    0.43
    Activations Density 2.350%

    No Known Activations