© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12793
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or trend

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    tonsoft
    -0.49
     oprot
    -0.47
     rhestr
    -0.47
     насељу
    -0.45
     فريبيس
    -0.44
    >{@
    -0.43
    nanoTime
    -0.42
     cuánt
    -0.42
    .}\
    -0.42
     OBITUARY
    -0.41
    POSITIVE LOGITS
    AndEndTag
    0.69
    Билгалдахарш
    0.68
    ::_('
    0.65
    تفصیلات
    0.64
     shift
    0.63
    存于互联网档案馆
    0.60
     @"/
    0.58
    irect
    0.58
    featureID
    0.57
     revenge
    0.57
    Activations Density 2.062%

    No Known Activations