© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5227
    Prev
    Next
    INDEX
    Explanations

    words related to trains and train stations

    oai_token-act-pair · gemini-2.0-flash

    train tracks and steps

    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
    ConstraintMaker
    -0.59
    ibus
    -0.58
     walks
    -0.58
     stepped
    -0.55
     walked
    -0.54
     Joni
    -0.54
    angliski
    -0.53
     Walks
    -0.51
    IntoConstraints
    -0.51
    walking
    -0.50
    POSITIVE LOGITS
    DeleteBehavior
    0.68
     препратки
    0.55
     antaranya
    0.50
     rozdí
    0.50
    loroethene
    0.49
    CloseOperation
    0.48
     telinga
    0.47
    esModule
    0.45
    MENAFN
    0.45
    SEC
    0.44
    Activations Density 1.274%

    No Known Activations