© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11468
    Prev
    Next
    INDEX
    Explanations

    mentions of "warnings" as well as titles

    oai_token-act-pair · gemini-2.0-flash

    warning

    np_max-act · gemini-2.0-flash
    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
     étoit
    -0.95
     vectorielle
    -0.95
     auroit
    -0.93
     Мексичка
    -0.93
     feroit
    -0.93
     étoient
    -0.92
     umana
    -0.92
     vettoriale
    -0.92
    CORBA
    -0.91
     pouvoit
    -0.91
    POSITIVE LOGITS
    t
    0.72
     will
    0.71
    ...
    0.71
    ton
    0.69
    a
    0.68
    bs
    0.63
    ly
    0.62
     direct
    0.62
     "
    0.61
     he
    0.60
    Activations Density 1.316%

    No Known Activations