© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13956
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gemini-2.0-flash

    Gratitude

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Jefus
    -1.16
    ValueStyle
    -1.03
     Majefty
    -1.02
     Diſ
    -0.95
     myſelf
    -0.95
    SharedDtor
    -0.94
     purpoſe
    -0.93
     ſtate
    -0.93
     Eſ
    -0.92
     Efq
    -0.91
    POSITIVE LOGITS
     M
    0.56
     a
    0.55
     Nat
    0.50
    M
    0.50
     ar
    0.46
    Nat
    0.45
    ofan
    0.39
    than
    0.39
     than
    0.38
     Ar
    0.38
    Activations Density 0.628%

    No Known Activations