© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4930
    Prev
    Next
    INDEX
    Explanations

    clauses with pronouns and words like "matter".

    oai_token-act-pair · gemini-2.0-flash

    Irrespective of conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     griega
    -0.67
    Whether
    -0.65
     démocr
    -0.64
     szint
    -0.64
    If
    -0.63
     giusti
    -0.63
     fermés
    -0.63
     stället
    -0.62
    where
    -0.61
     vœux
    -0.61
    POSITIVE LOGITS
    ]--;
    0.79
    PerformLayout
    0.75
    .*")]
    0.66
    ]++;
    0.64
    ThroughAttribute
    0.63
     يتيمه
    0.61
    awtextra
    0.59
    orial
    0.59
    NameInMap
    0.57
     onOptions
    0.57
    Activations Density 36.499%

    No Known Activations