© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6266
    Prev
    Next
    INDEX
    Explanations

    various words, punctuation and symbols indicating a rant, negative sentiment, or strong emotion, especially when related to a project or personal feelings.

    oai_token-act-pair · gemini-2.0-flash

    Expressing sadness

    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
     sadly
    -2.08
     unfortunately
    -1.97
     sad
    -1.86
    Sadly
    -1.77
    sad
    -1.77
     purtroppo
    -1.71
     Sadly
    -1.70
    Unfortunately
    -1.68
     regret
    -1.66
    unfortunately
    -1.66
    POSITIVE LOGITS
    philips
    0.45
    utilisons
    0.43
    њу
    0.42
    ues
    0.41
    ltk
    0.40
    extrême
    0.40
    ktır
    0.40
     tooth
    0.40
    หวัด
    0.40
    naver
    0.39
    Activations Density 2.502%

    No Known Activations