© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3302
    Prev
    Next
    INDEX
    Explanations

    late-night themes

    np_token-act-pair-logits · gpt-4o-mini

    mentions of news and late nights, particularly in a media context

    oai_token-act-pair · gemini-2.0-flash

    late

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    portál
    -0.43
    fortawesome
    -0.41
    μιουργ
    -0.41
    dafrika
    -0.41
     Walkover
    -0.41
    orija
    -0.40
    клопе
    -0.40
    }^{+\
    -0.40
    tisgarh
    -0.38
    )}+\
    -0.38
    POSITIVE LOGITS
     late
    2.86
    Late
    2.50
     Late
    2.44
     LATE
    2.38
    late
    2.38
    LATE
    2.05
     spät
    1.36
     позд
    1.27
    lates
    1.27
     midnight
    1.17
    Activations Density 2.659%

    No Known Activations