© 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. 10548
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and words associated with feelings or connection.

    oai_token-act-pair · gemini-2.0-flash

    year

    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
     <<<<<<<<<<<<<<
    -0.50
    ']))
    -0.50
     للاسماء
    -0.48
    .*")]
    -0.47
    ượng
    -0.46
    UnifiedTopology
    -0.45
    ⋙
    -0.45
    bof
    -0.43
    ])));
    -0.43
    }))
    -0.43
    POSITIVE LOGITS
     year
    2.06
    year
    1.68
    Year
    1.61
     Year
    1.60
     YEAR
    1.52
    YEAR
    1.41
     año
    1.30
     cra
    1.26
     année
    1.23
     Jahr
    1.16
    Activations Density 2.636%

    No Known Activations