© 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. 11589
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives or nouns followed by possessive "'s".

    oai_token-act-pair · gemini-2.0-flash

    Superlatives

    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
     world
    -1.25
    ValueStyle
    -1.05
     CommonModule
    -1.04
    world
    -1.03
    AsUp
    -1.01
    DeleteBehavior
    -0.99
     świata
    -0.94
     monde
    -0.93
    世界
    -0.91
    Jeografia
    -0.91
    POSITIVE LOGITS
     pre
    0.43
    ’
    0.37
    '
    0.35
    fa
    0.33
     procé
    0.30
     (
    0.30
    奈川
    0.29
    -(
    0.29
    тера
    0.28
     ~
    0.28
    Activations Density 0.732%

    No Known Activations