© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9824
    Prev
    Next
    INDEX
    Explanations

    words denoting change, progression, or conclusion

    oai_token-act-pair · gemini-2.0-flash

    describing change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    tagHelper
    -0.59
    BASEPATH
    -0.55
     avoit
    -0.55
    المشاركات
    -0.55
    adaptiveStyles
    -0.54
    hauled
    -0.51
    raised
    -0.51
    rawQuery
    -0.50
    WebControls
    -0.50
    Survi
    -0.50
    POSITIVE LOGITS
     becoming
    1.16
     coming
    1.03
    becoming
    0.99
     expanding
    0.96
     evolving
    0.94
     emerging
    0.94
     developing
    0.94
     getting
    0.94
     changing
    0.91
    coming
    0.91
    Activations Density 1.529%

    No Known Activations