© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4352
    Prev
    Next
    INDEX
    Explanations

    instances of someone asking for help or expressing a wish, especially in informal language.

    oai_token-act-pair · gemini-2.0-flash

    hope

    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
     you
    -1.73
    you
    -1.20
     vous
    -1.02
     YOU
    -0.97
     ur
    -0.96
     U
    -0.93
     You
    -0.93
     youre
    -0.89
    You
    -0.88
     você
    -0.82
    POSITIVE LOGITS
     AssemblyTitle
    0.72
    contentLoaded
    0.71
    NewUrlParser
    0.66
    LookAnd
    0.66
     preocupes
    0.66
     AppColors
    0.66
     kaarangay
    0.66
    noinspection
    0.64
     يتيمه
    0.63
     ―――――
    0.63
    Activations Density 1.702%

    No Known Activations