© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8182
    Prev
    Next
    INDEX
    Explanations

    segments of speech containing reporting verbs, conjunctions and pronouns

    oai_token-act-pair · gemini-2.0-flash

    Middle of conversation

    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
     They
    -1.00
     It
    -0.95
     Maybe
    -0.94
    They
    -0.94
    Maybe
    -0.92
     That
    -0.92
    That
    -0.92
    It
    -0.88
     Obviously
    -0.83
     When
    -0.81
    POSITIVE LOGITS
    日閲覧
    0.65
    
    0.64
    MENAFN
    0.62
    Portály
    0.60
    )}_{
    0.60
    ÉM
    0.59
    brainly
    0.58
    ()<<
    0.58
    )++;
    0.58
    WithIOException
    0.58
    Activations Density 9.555%

    No Known Activations