© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12661
    Prev
    Next
    INDEX
    Explanations

    words indicating importance or uniqueness

    oai_token-act-pair · gemini-2.0-flash

    relevant features or traits

    np_token-act-pair-logits · gpt-4o-mini

    quality or attribute

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     مرئيه
    -0.66
    色々と
    -0.60
     consultato
    -0.54
    いろいろ
    -0.54
    böz
    -0.53
    色々
    -0.52
    urança
    -0.51
     GenerationType
    -0.50
    Vanjske
    -0.49
     yii
    -0.49
    POSITIVE LOGITS
     feature
    1.15
     trait
    1.02
     symptom
    0.98
     option
    0.94
     ingredient
    0.93
    feature
    0.93
     tactic
    0.93
     requirement
    0.91
     attribute
    0.90
     suggestion
    0.88
    Activations Density 6.574%

    No Known Activations