© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3877
    Prev
    Next
    INDEX
    Explanations

    words related to self-help, personal growth, and coaching

    oai_token-act-pair · gemini-2.0-flash

    assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     estekak
    -0.79
     pinulongan
    -0.71
    StoryboardSegue
    -0.70
     transfieras
    -0.69
    ثيق
    -0.69
    UnknownFieldSet
    -0.66
    Hentet
    -0.65
    InvalidProtocol
    -0.65
    ValueStyle
    -0.62
    KommentareTeilen
    -0.60
    POSITIVE LOGITS
    <bos>
    0.48
    /*
    0.43
     gainera
    0.42
     ::=
    0.41
     gius
    0.40
     APPELLANT
    0.40
     EXAMIN
    0.40
     imagin
    0.40
    wiat
    0.40
    ragende
    0.40
    Activations Density 39.064%

    No Known Activations