© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11221
    Prev
    Next
    INDEX
    Explanations

    proper nouns or noun phrases, often capitalized and/or including numbers or punctuation

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Kre
    -0.84
     يتيمه
    -0.82
    VIAF
    -0.81
     vi
    -0.81
     der
    -0.81
     Ross
    -0.80
     Kon
    -0.79
     nas
    -0.79
     une
    -0.78
     Gardner
    -0.78
    POSITIVE LOGITS
     avoient
    1.07
     varandra
    1.05
     feroit
    1.03
     auroit
    1.02
     étoient
    0.94
     étoit
    0.92
     fermés
    0.91
     hendes
    0.89
     quelcon
    0.88
     giapp
    0.88
    Activations Density 15.260%

    No Known Activations