© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16152
    Prev
    Next
    INDEX
    Explanations

    the word "to" and words appearing near it.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · 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
    >{@
    -0.76
    KURZBESCHREIBUNG
    -0.71
    SharedDtor
    -0.70
    ResumeLayout
    -0.63
    textAppearance
    -0.63
     Pingback
    -0.62
    encils
    -0.60
     öppna
    -0.60
     дописавши
    -0.59
    cupertino
    -0.59
    POSITIVE LOGITS
     is
    0.52
    BeginContext
    0.45
    疫
    0.43
    GEBURTSDATUM
    0.40
     was
    0.39
     assi
    0.39
     pares
    0.38
     sem
    0.38
     International
    0.38
    AccessorTable
    0.38
    Activations Density 4.210%

    No Known Activations