© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 10448
    Prev
    Next
    INDEX
    Explanations

    mentions of subjectivity in movie reviews, especially when using words like "I", "my", and expressing sentiments or opinions

    oai_token-act-pair · gemini-2.0-flash

    negative opinions and sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    fra
    -0.50
    contentLoaded
    -0.45
    帖最后由
    -0.44
    oustics
    -0.42
    пря
    -0.40
     Gottesdienst
    -0.40
    kubectl
    -0.40
    тали
    -0.40
     Estadio
    -0.40
    all
    -0.38
    POSITIVE LOGITS
     للمعارف
    0.78
     المعيارى
    0.72
     tartalomajánló
    0.71
    })*/
    0.70
    $.}
    0.66
    hésite
    0.65
     Meksiku
    0.65
     مؤرشف
    0.61
    antaine
    0.61
    ]$}
    0.60
    Activations Density 6.928%

    No Known Activations