© 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. 11932
    Prev
    Next
    INDEX
    Explanations

    dates and numbers, especially those related to medical scenarios, sports scores, or historical events

    oai_token-act-pair · gemini-2.0-flash

    1

    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
    pushFollow
    -0.67
    rungsseite
    -0.56
    তথ্যসূত্র
    -0.52
    IntoConstraints
    -0.52
    UnusedPrivate
    -0.49
     androidx
    -0.46
    DropTable
    -0.45
     plaît
    -0.45
    InSection
    -0.44
    mbggenerated
    -0.43
    POSITIVE LOGITS
     photolibrary
    0.74
     Majefty
    0.67
     Muses
    0.65
     Phal
    0.63
    المكان
    0.63
     Membre
    0.62
     ་་
    0.61
     headboard
    0.60
     Samaria
    0.60
     فريبيس
    0.59
    Activations Density 1.236%

    No Known Activations