© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4794
    Prev
    Next
    INDEX
    Explanations

    mentions of government and politics, particularly the US government

    oai_token-act-pair · gemini-2.0-flash

    White House/war

    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
    St
    -0.35
    San
    -0.35
    Ob
    -0.34
    Imp
    -0.33
    Ad
    -0.30
    De
    -0.30
    Ne
    -0.30
    Bell
    -0.29
    Au
    -0.29
    Service
    -0.28
    POSITIVE LOGITS
     myſelf
    1.02
     themſelves
    0.98
     Monfieur
    0.96
     itſelf
    0.93
     poffible
    0.93
     himſelf
    0.91
     Theſe
    0.88
     Majefty
    0.87
    ſelf
    0.85
     whoſe
    0.84
    Activations Density 8.719%

    No Known Activations