© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5278
    Prev
    Next
    INDEX
    Explanations

    words related to protocols, mistakes, and revisions.

    oai_token-act-pair · gemini-2.0-flash

    procedure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ]));
    -0.55
    Przypisy
    -0.53
    Referencer
    -0.51
    :]:
    -0.51
     litté
    -0.50
    ']).
    -0.50
    "]);
    -0.48
     relever
    -0.48
    alva
    -0.48
    uxxxx
    -0.47
    POSITIVE LOGITS
     procedure
    1.05
     Procedure
    1.01
     procedures
    1.01
     Procedures
    0.94
     SOP
    0.94
    procedure
    0.92
     scripts
    0.90
     processes
    0.90
     protocol
    0.90
     protocols
    0.89
    Activations Density 1.567%

    No Known Activations