© 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. 12766
    Prev
    Next
    INDEX
    Explanations

    the word "variation"

    oai_token-act-pair · gemini-2.0-flash

    variation

    np_max-act · gemini-2.0-flash

    variation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     (
    -0.81
     I
    -0.76
     "
    -0.68
     Exacts
    -0.67
     
    -0.66
    :✨
    -0.59
     [
    -0.59
     '
    -0.59
     -
    -0.58
     \
    -0.58
    POSITIVE LOGITS
     myſelf
    1.15
     Efq
    1.13
     Theſe
    1.10
     ainfi
    1.09
     Anſ
    1.09
     feroit
    1.08
     Monfieur
    1.07
     Jefus
    1.06
     auroit
    1.05
     Reſ
    1.03
    Activations Density 3.643%

    No Known Activations