© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14264
    Prev
    Next
    INDEX
    Explanations

    words that indicate relative physical position in space or time

    oai_token-act-pair · gemini-2.0-flash

    prepositions of time/location

    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
    <bos>
    -0.85
    -
    -0.62
    .
    -0.57
    ↵↵
    -0.56
     and
    -0.55
    '
    -0.49
    /
    -0.48
    \
    -0.48
    *
    -0.46
     to
    -0.46
    POSITIVE LOGITS
     مشين
    1.20
     AssemblyTitle
    1.12
    ContentAsync
    1.09
    -------
    1.07
     EconPapers
    1.03
    complexContent
    1.02
    +#+#
    1.01
    
    1.00
     مرئيه
    0.98
    providedIn
    0.98
    Activations Density 0.301%

    No Known Activations