© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4155
    Prev
    Next
    INDEX
    Explanations

    the word "close" or phrases with "close" and words indicating proximity

    oai_token-act-pair · gemini-2.0-flash

    relationships, proximity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     kasarigan
    -0.78
     المعيارى
    -0.71
    orianCalendar
    -0.71
     Monfieur
    -0.70
    Portail
    -0.70
     Efq
    -0.70
    ApiModelProperty
    -0.64
     Portail
    -0.62
     חיצוניים
    -0.61
     Blockly
    -0.60
    POSITIVE LOGITS
     بيها
    0.50
    itse
    0.44
     com
    0.44
    évaluateur
    0.44
     κό
    0.42
    piram
    0.41
    lå
    0.41
    back
    0.40
     mk
    0.40
    ématique
    0.40
    Activations Density 2.570%

    No Known Activations