© 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. 13222
    Prev
    Next
    INDEX
    Explanations

    the passive voice, especially around words like "founded", "created", and "invented"

    oai_token-act-pair · gemini-2.0-flash

    was

    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
     CallOverrides
    -0.56
    PerformLayout
    -0.56
     >=",
    -0.53
     lenker
    -0.52
     سكانية
    -0.50
    StructEnd
    -0.50
     createStore
    -0.49
    ]")]
    -0.49
    >>();
    -0.48
    bollah
    -0.48
    POSITIVE LOGITS
     firſt
    0.69
     fubject
    0.69
     ſmall
    0.65
     purpoſe
    0.64
    fører
    0.63
     quæ
    0.57
     pleaſure
    0.57
    +:+
    0.56
    deelte
    0.56
     laſt
    0.56
    Activations Density 5.491%

    No Known Activations