© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9844
    Prev
    Next
    INDEX
    Explanations

    sentences containing words that express strong opinions or agreement and/or disagreement.

    oai_token-act-pair · gemini-2.0-flash

    Adjectives and over-exaggeration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     completely
    -2.11
     totally
    -2.06
     Completely
    -1.93
     Totally
    -1.92
    totally
    -1.91
    Completely
    -1.90
    completely
    -1.90
    Totally
    -1.83
     entirely
    -1.81
     completamente
    -1.63
    POSITIVE LOGITS
    PerformLayout
    0.81
     فريبيس
    0.70
    BorderFactory
    0.69
    AutoScaleMode
    0.66
    prefixer
    0.59
     виправивши
    0.58
    +#+#
    0.56
    setta
    0.56
     CommonModule
    0.56
    ForResult
    0.54
    Activations Density 3.083%

    No Known Activations