© 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. 11786
    Prev
    Next
    INDEX
    Explanations

    something vaguely related to passive voice, "to" as a preposition, variables, measurements, and science terminology

    oai_token-act-pair · gemini-2.0-flash

    Scientific procedures and instructions

    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
     يتيمه
    -0.44
     She
    -0.43
    گي
    -0.39
     T
    -0.39
     M
    -0.38
    heel
    -0.37
    T
    -0.37
    ant
    -0.37
     ex
    -0.36
    She
    -0.35
    POSITIVE LOGITS
    UnusedPrivate
    0.95
     Efq
    0.94
     ―――――
    0.79
    ^(@)
    0.79
     Chriftian
    0.74
     myſelf
    0.74
     pleaſure
    0.71
    ItemBackground
    0.71
     greateſt
    0.71
     itſelf
    0.71
    Activations Density 0.320%

    No Known Activations