© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2915
    Prev
    Next
    INDEX
    Explanations

    the word "straight".

    oai_token-act-pair · gemini-2.0-flash

    straight

    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
    Negative Logits
    Collegamenti
    -0.50
     BREAK
    -0.49
     Breaker
    -0.49
     Break
    -0.48
    НИК
    -0.47
    Tracce
    -0.47
    Break
    -0.46
     Klassi
    -0.45
    anyol
    -0.45
    pageX
    -0.45
    POSITIVE LOGITS
    DoubleQuotes
    0.94
     HasFactory
    0.68
    CloseOperation
    0.65
     '\\;'
    0.62
    featureID
    0.61
     مشين
    0.60
    φάλ
    0.60
    )}</
    0.58
    URLException
    0.57
     GenerationType
    0.57
    Activations Density 1.220%

    No Known Activations