© 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. 5460
    Prev
    Next
    INDEX
    Explanations

    internet addresses or URLs

    oai_token-act-pair · gemini-2.0-flash

    internet domains

    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
     kasarigan
    -1.05
     ExecuteAsync
    -0.89
    ThroughAttribute
    -0.77
    migrationBuilder
    -0.77
    Życiorys
    -0.75
     snippetHide
    -0.68
    })*/
    -0.67
     Roskov
    -0.67
     bezeichneter
    -0.67
     مرئيه
    -0.65
    POSITIVE LOGITS
     en
    1.08
    en
    0.90
     de
    0.69
    ru
    0.62
     fr
    0.62
     EN
    0.61
    EN
    0.60
     En
    0.59
    En
    0.56
     ja
    0.55
    Activations Density 0.509%

    No Known Activations