© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11389
    Prev
    Next
    INDEX
    Explanations

    words and phrases from self-help style speeches, marketing, or political rhetoric.

    oai_token-act-pair · gemini-2.0-flash

    quotations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Kendra
    -0.75
     Archaeological
    -0.75
     Toys
    -0.73
     pulpit
    -0.73
     throne
    -0.73
    bali
    -0.73
    KURZBESCHREIBUNG
    -0.73
    ]--;
    -0.72
     Chicano
    -0.72
     chén
    -0.71
    POSITIVE LOGITS
    fortawesome
    0.35
     CreateTagHelper
    0.34
    PerformLayout
    0.28
    antaranya
    0.28
    #
    0.27
     FetchType
    0.27
    なか
    0.26
     esternos
    0.26
    ScopeManager
    0.26
     venido
    0.25
    Activations Density 4.093%

    No Known Activations