© 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. 3215
    Prev
    Next
    INDEX
    Explanations

    words related to professions, training, and studies of groups of people

    oai_token-act-pair · gemini-2.0-flash

    professional

    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
    Jeografia
    -0.60
     Schicht
    -0.57
     icke
    -0.56
    ريات
    -0.55
    OGND
    -0.55
     récol
    -0.53
    colazione
    -0.53
     moyens
    -0.53
    atteindre
    -0.52
     wechsel
    -0.51
    POSITIVE LOGITS
     BitmapFactory
    0.66
    zzleHttp
    0.63
    elemField
    0.60
    __(/*!
    0.60
    /**
    0.53
    Jegyzetek
    0.53
    nonatomic
    0.52
    iastes
    0.50
     BoxFit
    0.50
     Taktlose
    0.49
    Activations Density 2.017%

    No Known Activations