© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12690
    Prev
    Next
    INDEX
    Explanations

    words beginning with "aff" or "Af"

    oai_token-act-pair · gemini-2.0-flash

    Legal, genetics, race

    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
     nakalista
    -0.65
     Qu
    -0.59
     Co
    -0.56
    SequentialGroup
    -0.53
     co
    -0.51
     EconPapers
    -0.50
    Slf
    -0.49
    قایناق‌لار
    -0.49
    Viited
    -0.47
    arXiv
    -0.47
    POSITIVE LOGITS
    propTypes
    0.58
     LSM
    0.57
    recated
    0.54
     Fordham
    0.53
    VersionUID
    0.53
    hower
    0.52
     FontWeight
    0.51
    المناصب
    0.51
    }();
    0.51
     تكبرها
    0.51
    Activations Density 0.275%

    No Known Activations