© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5017
    Prev
    Next
    INDEX
    Explanations

    words/phrases used when asking for advice or projecting into the future.

    oai_token-act-pair · 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
     only
    -0.65
     kasarigan
    -0.56
    DeleteBehavior
    -0.55
    Ellips
    -0.54
    Diwedd
    -0.52
    CommandText
    -0.51
    only
    -0.49
     tikai
    -0.47
     soltanto
    -0.46
    Viited
    -0.46
    POSITIVE LOGITS
    ViewFeatures
    0.78
    tagHelperRunner
    0.69
    MarshalTo
    0.61
    ConstraintMaker
    0.61
    SBATCH
    0.60
    BindView
    0.59
    protoc
    0.58
    }()
    0.57
    xase
    0.57
    +#+#
    0.56
    Activations Density 13.744%

    No Known Activations