© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9762
    Prev
    Next
    INDEX
    Explanations

    the topic of coffee and its accoutrements

    oai_token-act-pair · gemini-2.0-flash

    milky

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     ſche
    -0.59
    adaptiveStyles
    -0.58
     Efq
    -0.57
     ſtate
    -0.56
     }_{\
    -0.55
     purpoſe
    -0.54
    endgroup
    -0.53
     ſtre
    -0.53
     sportive
    -0.52
     cauſe
    -0.52
    POSITIVE LOGITS
    PINES
    0.58
    Portail
    0.58
    ########.
    0.56
    kuuta
    0.55
    printLine
    0.52
    jspb
    0.52
    
    0.51
    بوابة
    0.50
    Vaata
    0.50
    tanleria
    0.49
    Activations Density 0.528%

    No Known Activations