© 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. 9450
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to political disagreements and conflict

    oai_token-act-pair · gemini-2.0-flash

    territorial conflicts and negotiations

    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
    SequentialGroup
    -0.56
    úrate
    -0.52
    dani
    -0.51
    SizeF
    -0.49
    IVEREF
    -0.48
     lead
    -0.47
     dove
    -0.47
    BeginContext
    -0.47
    annah
    -0.47
     كمان
    -0.45
    POSITIVE LOGITS
     Roskov
    0.56
    Искәрмәләр
    0.52
     Developed
    0.52
    שמי
    0.52
    Developed
    0.50
    IntoConstraints
    0.50
    FilterChain
    0.49
     semblables
    0.49
    rungsseite
    0.47
     alami
    0.47
    Activations Density 10.211%

    No Known Activations