© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7291
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to personal experiences, feelings, and opinions

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Mad
    -0.44
    ArgsConstructor
    -0.43
    fluid
    -0.42
     Fluid
    -0.42
    Comfortable
    -0.41
    Mad
    -0.40
     emot
    -0.40
    SupportActionBar
    -0.40
     Fluids
    -0.39
     fap
    -0.39
    POSITIVE LOGITS
     Италијани
    0.85
    SourceChecksum
    0.75
    TypedDataSet
    0.69
    GEBURTSDATUM
    0.68
    Referències
    0.66
    tagHelperRunner
    0.66
    DBNull
    0.65
    WithIOException
    0.64
    Distribuzione
    0.63
    Népesség
    0.62
    Activations Density 7.045%

    No Known Activations