© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12782
    Prev
    Next
    INDEX
    Explanations

    restaurant and travel reviews and/or related language.

    oai_token-act-pair · gemini-2.0-flash

    "pre/base"

    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
    MLLoader
    -0.89
     ―――――
    -0.83
     iſt
    -0.77
     EconPapers
    -0.77
     ſind
    -0.75
     Efq
    -0.74
     Forumite
    -0.73
     Theſe
    -0.73
     Monfieur
    -0.73
    IUrlHelper
    -0.72
    POSITIVE LOGITS
     Pre
    0.59
     pre
    0.58
     end
    0.56
     based
    0.54
    rimas
    0.54
    pre
    0.52
     to
    0.52
    Base
    0.51
     Base
    0.50
     base
    0.49
    Activations Density 3.250%

    No Known Activations