© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11715
    Prev
    Next
    INDEX
    Explanations

    the word "there", "you", "what", "we", and "effort"

    oai_token-act-pair · gemini-2.0-flash

    should

    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
    曖昧さ回避
    -0.62
     GONNA
    -0.60
     is
    -0.59
     will
    -0.55
    ativement
    -0.53
     needs
    -0.50
     van
    -0.50
    Datuak
    -0.49
     are
    -0.49
     Gotta
    -0.49
    POSITIVE LOGITS
     should
    0.89
     shou
    0.73
    InjectAttribute
    0.71
     sh
    0.70
     sho
    0.68
     Sollte
    0.66
    Should
    0.66
     shu
    0.66
    should
    0.63
     Should
    0.62
    Activations Density 0.078%

    No Known Activations