© 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. 14083
    Prev
    Next
    INDEX
    Explanations

    geographical information about Poland, as well as the term "web"

    oai_token-act-pair · gemini-2.0-flash

    proper nouns and locations

    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
    migrationBuilder
    -0.63
    ⓧ
    -0.61
     DPRD
    -0.60
    
    -0.60
    ondere
    -0.59
    aimer
    -0.57
    zian
    -0.54
     protoimpl
    -0.53
    rafts
    -0.53
     sī
    -0.53
    POSITIVE LOGITS
     geldig
    0.45
     fiducia
    0.45
     примеру
    0.45
     ajudá
    0.45
     recuerdos
    0.44
    XtraBars
    0.41
     houver
    0.41
     autorité
    0.41
    styleType
    0.40
     acusa
    0.40
    Activations Density 0.558%

    No Known Activations