© 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. 12783
    Prev
    Next
    INDEX
    Explanations

    personal ads or descriptions of people.

    oai_token-act-pair · gemini-2.0-flash

    someone

    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
    something
    -1.42
     something
    -1.36
     Something
    -1.31
    Something
    -1.30
     algo
    -0.94
     quelque
    -0.90
     något
    -0.86
     SOMETHING
    -0.86
     iets
    -0.83
     qualcosa
    -0.79
    POSITIVE LOGITS
     someone
    1.63
     Someone
    1.35
    Someone
    1.33
    someone
    1.22
     SOMEONE
    0.99
     somebody
    0.93
     iemand
    0.90
     quelqu
    0.88
     alguien
    0.84
     alguém
    0.81
    Activations Density 1.847%

    No Known Activations