© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7687
    Prev
    Next
    INDEX
    Explanations

    speech surrounded by quotes

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    writeFieldEnd
    -0.61
    Ecotoxicity
    -0.58
     vPvB
    -0.57
    FailureListener
    -0.54
    IsPostBack
    -0.51
    ・)
    -0.50
     disponibilités
    -0.49
     informée
    -0.48
    datatables
    -0.47
    CompleteListener
    -0.47
    POSITIVE LOGITS
     His
    2.38
    His
    2.09
     Her
    1.98
     Your
    1.92
    Her
    1.83
    Your
    1.68
     Their
    1.67
    YOUR
    1.46
     HIS
    1.46
     YOUR
    1.41
    Activations Density 3.612%

    No Known Activations