© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3879
    Prev
    Next
    INDEX
    Explanations

    code and code documentation elements

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -1.12
     itſelf
    -1.08
     pleaſure
    -1.05
     myſelf
    -1.02
     виправивши
    -1.00
    .")
    -0.99
     purpoſe
    -0.97
     houſe
    -0.97
     Jefus
    -0.95
     ་་
    -0.94
    POSITIVE LOGITS
     May
    0.98
     Can
    0.84
     Will
    0.76
    May
    0.72
     Be
    0.71
     Make
    0.69
     
    0.68
     Has
    0.66
    ↵↵
    0.66
    ↵
    0.65
    Activations Density 6.253%

    No Known Activations