© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5208
    Prev
    Next
    INDEX
    Explanations

    mentions of communication.

    oai_token-act-pair · gemini-2.0-flash

    describing/naming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    صرية
    -0.57
    cargas
    -0.53
    انيف
    -0.51
     calda
    -0.50
     sendo
    -0.49
     désolés
    -0.49
     väli
    -0.44
    份
    -0.44
     là
    -0.44
     Là
    -0.43
    POSITIVE LOGITS
    AddTagHelper
    0.79
    Portale
    0.67
    ]));
    0.63
     kasarigan
    0.62
     Superhost
    0.59
    Билгалдахарш
    0.57
     समीक्षक
    0.57
    ThroughAttribute
    0.56
     &___
    0.56
     defaultstate
    0.56
    Activations Density 4.615%

    No Known Activations