© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12905
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and quantities

    oai_token-act-pair · gemini-2.0-flash

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    PreferredItem
    -0.96
    Personendaten
    -0.90
     kasarigan
    -0.81
    tanleria
    -0.81
    EndGlobalSection
    -0.80
     ComVisible
    -0.74
    afficheront
    -0.72
    addCriterion
    -0.72
     Walkover
    -0.70
     Wikimedijinoj
    -0.69
    POSITIVE LOGITS
    kraft
    0.44
    GLOBALS
    0.44
    ucus
    0.43
    anin
    0.43
    setPreferred
    0.42
    BERG
    0.42
    équi
    0.41
     devi
    0.41
    individu
    0.40
    ADOS
    0.40
    Activations Density 7.494%

    No Known Activations