© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16281
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns with a weak preference for "own"

    oai_token-act-pair · gemini-2.0-flash

    say "own"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     its
    -2.30
    Its
    -1.78
     own
    -1.63
     Its
    -1.63
    its
    -1.59
    own
    -1.55
     their
    -1.43
    Own
    -1.39
    自己的
    -1.36
     Own
    -1.36
    POSITIVE LOGITS
     very
    0.57
     ain
    0.46
     personal
    0.45
     useState
    0.42
     très
    0.42
    very
    0.40
     don
    0.40
    -
    0.40
     private
    0.38
    JsonHelper
    0.38
    Activations Density 1.157%

    No Known Activations