© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6173
    Prev
    Next
    INDEX
    Explanations

    phrases of doubt and uncertainty

    oai_token-act-pair · gemini-2.0-flash

    Expressing doubt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     protoimpl
    -0.70
     виправивши
    -0.69
     itſelf
    -0.58
    AndEndTag
    -0.58
    HomeAsUpEnabled
    -0.57
    سطس
    -0.56
     AssemblyCulture
    -0.56
    detectChanges
    -0.56
     otomatig
    -0.55
    MessageOf
    -0.55
    POSITIVE LOGITS
     doubt
    1.98
     doubts
    1.69
    doubt
    1.68
     Doubt
    1.54
     doubted
    1.38
    Doubt
    1.38
     doute
    1.33
     doubtful
    1.31
     сом
    1.30
     duda
    1.23
    Activations Density 2.111%

    No Known Activations