© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12526
    Prev
    Next
    INDEX
    Explanations

    the word 'doors'

    oai_token-act-pair · gemini-2.0-flash

    doors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     يتيمه
    -1.10
    migrationBuilder
    -1.08
    WithIOException
    -1.07
     HasFactory
    -1.02
    Espèce
    -1.01
    ंदीखरीदारी
    -1.00
     EconPapers
    -1.00
     Audiodateien
    -0.99
     لينك
    -0.98
    RenderAtEndOf
    -0.97
    POSITIVE LOGITS
    ing
    0.63
     cor
    0.63
     for
    0.63
     to
    0.59
     control
    0.57
    ous
    0.56
     hard
    0.56
    .
    0.56
     similar
    0.54
    ↵
    0.53
    Activations Density 1.597%

    No Known Activations