© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6817
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns such as his/hers/theirs, but not yours

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    osoever
    -0.81
    endphp
    -0.79
    Filmografia
    -0.73
    HttpFoundation
    -0.73
     Anyways
    -0.73
    ttino
    -0.71
    ORIAL
    -0.70
     Efq
    -0.69
    enapa
    -0.69
    Anyways
    -0.66
    POSITIVE LOGITS
    <bos>
    0.67
     her
    0.63
     my
    0.52
    彼女の
    0.47
     насеље
    0.46
    '],$
    0.46
    tainen
    0.44
    my
    0.43
     she
    0.42
     ferner
    0.42
    Activations Density 0.287%

    No Known Activations