© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13556
    Prev
    Next
    INDEX
    Explanations

    the word "review"

    oai_token-act-pair · gemini-2.0-flash

    review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     review
    -2.80
    review
    -2.47
     Review
    -2.45
    Review
    -2.44
     REVIEW
    -2.13
     reviewed
    -2.03
     reviewing
    -1.95
    REVIEW
    -1.93
     reviews
    -1.84
     Reviewing
    -1.56
    POSITIVE LOGITS
     ""],
    0.77
    sidemargin
    0.65
    addContainerGap
    0.58
    (',');
    0.56
    smöglichkeiten
    0.55
     '/':
    0.54
     vastu
    0.54
    ership
    0.54
     ''}
    0.54
    hages
    0.53
    Activations Density 0.322%

    No Known Activations