© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15943
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with current events or situations.

    oai_token-act-pair · gemini-2.0-flash

    varied snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     nakalista
    -0.85
     Мексичка
    -0.83
     Efq
    -0.82
     Monfieur
    -0.82
     Reſ
    -0.79
     gypsum
    -0.79
     Shakspeare
    -0.78
     Anſ
    -0.75
     Houſe
    -0.75
     DCM
    -0.72
    POSITIVE LOGITS
     >=",
    0.56
     ready
    0.47
     bore
    0.46
    leté
    0.45
     WAS
    0.45
    λοι
    0.45
     LATER
    0.45
     SURE
    0.44
     GUYS
    0.44
     OR
    0.43
    Activations Density 21.629%

    No Known Activations