© 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. 15596
    Prev
    Next
    INDEX
    Explanations

    dialogue indicators, such as quotation marks, names followed by titles,and terms of affection

    oai_token-act-pair · gemini-2.0-flash

    Terms of endearment

    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
     дописавши
    -0.65
    XtraEditors
    -0.60
     sir
    -0.58
     ExecuteAsync
    -0.57
     brother
    -0.57
    ValueStyle
    -0.56
    ########.
    -0.55
    +#+#
    -0.54
    sizeCache
    -0.54
     bağlantılar
    -0.54
    POSITIVE LOGITS
     ma
    1.00
     Ma
    0.92
    Ma
    0.89
    ma
    0.74
    MA
    0.67
     MA
    0.66
     Sis
    0.65
    maw
    0.63
    Sis
    0.60
     honey
    0.58
    Activations Density 6.201%

    No Known Activations