© 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. 12509
    Prev
    Next
    INDEX
    Explanations

    tokens that follow the word "this" or are related to sadness/upset

    oai_token-act-pair · 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
    makes
    -1.10
    make
    -1.08
     make
    -1.07
    Makes
    -1.02
     Makes
    -0.99
     makes
    -0.96
     MAKES
    -0.95
    Make
    -0.92
     MAKE
    -0.92
     Make
    -0.90
    POSITIVE LOGITS
     Administrativna
    0.52
    Зноскі
    0.52
    ::_('
    0.51
     >=",
    0.51
    에는
    0.50
     nonatomic
    0.47
    toja
    0.46
    kreuz
    0.46
    DAOImpl
    0.45
    Билгалдахарш
    0.44
    Activations Density 3.322%

    No Known Activations