© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12625
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, especially in positive contexts.

    oai_token-act-pair · gemini-2.0-flash

    get

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    IBarButtonItem
    -0.63
     Италијани
    -0.63
     Administrativna
    -0.63
     BoxFit
    -0.62
    клопе
    -0.59
     Krakowie
    -0.57
     Ingles
    -0.55
    chiali
    -0.54
     المعيارى
    -0.54
     հղումներ
    -0.54
    POSITIVE LOGITS
     get
    2.19
    get
    1.99
     gets
    1.95
     Get
    1.80
    Get
    1.70
     Gets
    1.63
     getting
    1.63
    gets
    1.57
     GET
    1.57
     Getting
    1.49
    Activations Density 2.490%

    No Known Activations