© 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. 12350
    Prev
    Next
    INDEX
    Explanations

    words related to measurements of space and time and words ending in ers

    oai_token-act-pair · 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
     للمعارف
    -0.84
     MatDialog
    -0.71
    Diweddarwch
    -0.66
     getopt
    -0.65
    Hozzáférés
    -0.62
     DialogResult
    -0.62
    RenderAtEndOf
    -0.60
    PhysRevD
    -0.60
     Reverso
    -0.59
    AndEndTag
    -0.59
    POSITIVE LOGITS
    λους
    0.56
     kind
    0.52
     sortes
    0.47
     HasFactory
    0.47
     vervangen
    0.46
    TypeService
    0.46
    Obituary
    0.46
     Mau
    0.46
    poch
    0.45
     Besitz
    0.45
    Activations Density 1.388%

    No Known Activations