© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13063
    Prev
    Next
    INDEX
    Explanations

    words related to death and the macabre

    oai_token-act-pair · gemini-2.0-flash

    skeletons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     proportion
    -0.57
     păr
    -0.55
     samples
    -0.53
     Garnet
    -0.51
    /**
    -0.50
     consigo
    -0.50
    ruptedException
    -0.50
    ณี
    -0.49
     prosent
    -0.49
    samples
    -0.49
    POSITIVE LOGITS
     Roskov
    0.78
    GenerationType
    0.66
    CloseOperation
    0.65
     TextAppearance
    0.63
    RenderAtEndOf
    0.60
     defaultstate
    0.57
    ExecuteReader
    0.57
     LoggerFactory
    0.56
    ')):
    0.55
    Personensuche
    0.54
    Activations Density 0.944%

    No Known Activations