© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16146
    Prev
    Next
    INDEX
    Explanations

    the word "suspect" and words near it that might imply a possible action

    oai_token-act-pair · gemini-2.0-flash

    suspect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -1.12
    ↵
    -0.87
    '
    -0.81
    .
    -0.80
    <eos>
    -0.79
    (
    -0.70
    ↵↵↵
    -0.70
    -
    -0.65
     
    -0.63
    ↵↵↵↵
    -0.63
    POSITIVE LOGITS
    SequentialGroup
    1.24
     चीज़ों
    1.20
     auroit
    1.17
    tagHelperRunner
    1.16
    JspWriter
    1.14
     feroit
    1.14
     ExecuteAsync
    1.14
    //});
    1.13
     étoit
    1.10
    ஡
    1.09
    Activations Density 1.658%

    No Known Activations