© 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. 6978
    Prev
    Next
    INDEX
    Explanations

    words or multi-word phrases indicating something's original state or difficult to understand

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
     initial
    -2.39
     original
    -2.25
    initial
    -2.22
    Initial
    -2.20
     initially
    -2.19
     Initial
    -2.14
    original
    -2.08
    Original
    -2.08
     Initially
    -2.00
     Original
    -1.98
    POSITIVE LOGITS
     OR
    0.47
    ousa
    0.37
    گون
    0.37
    ¡
    0.36
     vinto
    0.35
    CORBA
    0.34
     Or
    0.34
    gei
    0.34
     silueta
    0.34
    Or
    0.33
    Activations Density 1.566%

    No Known Activations