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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14515
    Prev
    Next
    INDEX
    Explanations

    uses of "their" and words related to slavery

    oai_token-act-pair · gemini-2.0-flash

    there

    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
    +#+#
    -0.61
    Identyfik
    -0.55
    GEBURTS
    -0.50
    ----</
    -0.49
     correctes
    -0.49
     चीज़ों
    -0.48
    KommentareTeilen
    -0.48
    ➟
    -0.47
    AFM
    -0.46
    ものを
    -0.45
    POSITIVE LOGITS
     there
    4.00
    there
    3.34
     THERE
    2.97
    There
    2.86
     There
    2.78
    THERE
    2.55
     هناك
    2.09
     thither
    1.85
    theres
    1.70
     theres
    1.65
    Activations Density 6.343%

    No Known Activations