© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4191
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns like "her," "his," "their," and "your," sometimes in conjunction with "own."

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns followed by "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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     your
    -2.14
     his
    -2.09
     their
    -1.84
     her
    -1.77
    your
    -1.66
     my
    -1.60
     our
    -1.59
    his
    -1.58
    their
    -1.49
     its
    -1.44
    POSITIVE LOGITS
    Sucesor
    0.59
    Condol
    0.52
     CanadaChoose
    0.52
    Ārējās
    0.51
    CompilerServices
    0.48
     يتيمه
    0.48
    ILayout
    0.48
     Meksiku
    0.47
    /**
    0.47
    ArgsConstructor
    0.47
    Activations Density 2.408%

    No Known Activations