© 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. 5773
    Prev
    Next
    INDEX
    Explanations

    superlative phrases and the word "the".

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     Efq
    -0.96
    rungsseite
    -0.90
    MigrationBuilder
    -0.85
     onData
    -0.80
    AsUp
    -0.79
     Monfieur
    -0.77
     Jefus
    -0.77
    zzleHttp
    -0.76
     Theſe
    -0.76
    ⓧ
    -0.75
    POSITIVE LOGITS
     most
    0.63
     single
    0.62
    single
    0.52
    Single
    0.51
     Single
    0.51
     Most
    0.48
    Most
    0.47
    язы
    0.45
    most
    0.44
    jScrollPane
    0.40
    Activations Density 1.149%

    No Known Activations