© 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. 1875
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to negative or critical sentiment or uncertainty in reviews, specifically in a comparative or evaluative context

    oai_token-act-pair · gemini-2.0-flash

    negative sentiment

    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
    InjectAttribute
    -0.63
    principalColumn
    -0.61
    alyptus
    -0.58
     subtilis
    -0.57
     JADX
    -0.56
    ]")]
    -0.56
    typeorm
    -0.56
    awtextra
    -0.54
    makeText
    -0.53
    الإنجليزية
    -0.53
    POSITIVE LOGITS
     civili
    0.50
    runOnUiThread
    0.50
    แห
    0.49
     schul
    0.48
    jaman
    0.48
    Приятного
    0.47
     civi
    0.47
     Ravenna
    0.46
     Clon
    0.46
     bayan
    0.46
    Activations Density 2.170%

    No Known Activations