© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4392
    Prev
    Next
    INDEX
    Explanations

    uses of "I am" and "what" referring to people's experience

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb "to be."

    np_token-act-pair-logits · gpt-4o-mini

    Variations of "become"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     poffible
    -0.56
     familiarity
    -0.56
    FieldBuilder
    -0.54
     Familiar
    -0.53
     الرياضيه
    -0.52
     EClass
    -0.51
    AndEndTag
    -0.51
     saites
    -0.51
    principalTable
    -0.50
    ніципалі
    -0.49
    POSITIVE LOGITS
     is
    0.85
     become
    0.69
     Become
    0.67
    Become
    0.63
    tagHelperRunner
    0.63
    become
    0.62
     becoming
    0.60
     Becoming
    0.60
     are
    0.59
    aspectj
    0.57
    Activations Density 1.396%

    No Known Activations