© 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. 15339
    Prev
    Next
    INDEX
    Explanations

    the word "vision" and related words such as "plans" and "positioning"

    oai_token-act-pair · gemini-2.0-flash

    vision

    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
     שוליים
    -0.98
    yship
    -0.93
    moiselle
    -0.85
    adays
    -0.81
     生命周期
    -0.73
    djangoproject
    -0.72
     StatelessWidget
    -0.71
    soever
    -0.71
     unknownFields
    -0.71
    homonymie
    -0.70
    POSITIVE LOGITS
     the
    0.90
     this
    0.67
     what
    0.65
     between
    0.63
    er
    0.57
     your
    0.56
    en
    0.55
     below
    0.55
     over
    0.55
     and
    0.55
    Activations Density 1.812%

    No Known Activations