© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12262
    Prev
    Next
    INDEX
    Explanations

    the words 'the', 'in', 'and', 'with', and 'control' as well as phrases indicating a comparison between two groups.

    oai_token-act-pair · gemini-2.0-flash

    experimental vs control

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    LookAnd
    -0.70
     يتيمه
    -0.70
    \{\\
    -0.68
     ModelExpression
    -0.68
    تقاوى
    -0.66
     pinulongan
    -0.61
    InvalidProtocol
    -0.61
    SequentialGroup
    -0.60
     nahilalakip
    -0.60
     Réponses
    -0.59
    POSITIVE LOGITS
    Toole
    0.55
    BeginContext
    0.50
    GRAFIA
    0.50
    alleria
    0.48
    rifugal
    0.48
    ]++;
    0.46
    onson
    0.45
     boca
    0.45
     cheat
    0.44
    INTENANCE
    0.44
    Activations Density 8.054%

    No Known Activations