© 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. 6818
    Prev
    Next
    INDEX
    Explanations

    words that are associated with arguments and political topics

    oai_token-act-pair · gemini-2.0-flash

    CAM

    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
    HAVE
    -0.66
    have
    -0.65
    Have
    -0.63
     Have
    -0.56
     épis
    -0.56
     automatiques
    -0.54
     béné
    -0.54
     geef
    -0.53
     médicaux
    -0.53
     HAVE
    -0.53
    POSITIVE LOGITS
     work
    1.02
     drive
    0.85
     play
    0.85
     pay
    0.85
     stand
    0.81
     stick
    0.78
     fight
    0.77
     wear
    0.77
     display
    0.76
     escape
    0.76
    Activations Density 12.505%

    No Known Activations