© 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. 4519
    Prev
    Next
    INDEX
    Explanations

    various uses of the word "tell" and similar words/grammar such as expressing gratitude, introducing topics, preparation, and making statements.

    oai_token-act-pair · gemini-2.0-flash

    "us" in many languages

    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
     Me
    -0.82
    Me
    -0.81
    me
    -0.79
    myself
    -0.72
    my
    -0.68
     Myself
    -0.68
     Mej
    -0.67
    ME
    -0.66
     myself
    -0.65
     Meine
    -0.65
    POSITIVE LOGITS
     us
    2.95
     Us
    1.69
    us
    1.59
    Us
    1.48
     нас
    1.24
     nous
    1.21
     нам
    1.16
     нами
    1.09
     nosotros
    1.06
     nás
    1.02
    Activations Density 2.126%

    No Known Activations