© 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. 11095
    Prev
    Next
    INDEX
    Explanations

    language used to conduct academic studies, especially phrases indicating the validity and generalization of the study

    oai_token-act-pair · gemini-2.0-flash

    likely

    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
     disambiguazione
    -0.98
    AsUp
    -0.80
     للمعارف
    -0.64
    IntoConstraints
    -0.62
    AndEndTag
    -0.62
    devamını
    -0.60
    (!__
    -0.59
    Viitteet
    -0.59
     تانيه
    -0.59
    তথ্যসূত্র
    -0.57
    POSITIVE LOGITS
     likely
    2.52
    likely
    2.14
     Likely
    1.95
    Likely
    1.68
     LIK
    1.27
     likelihood
    1.04
     wahrscheinlich
    0.93
     waarschijnlijk
    0.91
     probable
    0.90
     kemungkinan
    0.87
    Activations Density 9.021%

    No Known Activations