© 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. 10997
    Prev
    Next
    INDEX
    Explanations

    a variety of words related to mountains and rocks, as well as coding notation

    oai_token-act-pair · gemini-2.0-flash

    Outdoor activities

    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
    rafo
    -0.40
     cref
    -0.39
    циони
    -0.35
    }}%
    -0.35
    ]()
    -0.35
    ()")
    -0.35
    водства
    -0.34
    ;");
    -0.34
    __]
    -0.33
     SwiftUI
    -0.33
    POSITIVE LOGITS
     nonatomic
    0.81
    GEBURTSDATUM
    0.72
    uxxxx
    0.71
     ویکی‌پدی
    0.68
     Monfieur
    0.65
     كومونز
    0.65
    NameInMap
    0.63
    nitten
    0.63
     Anſ
    0.63
    yarnpkg
    0.62
    Activations Density 0.660%

    No Known Activations