© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6266
    Prev
    Next
    INDEX
    Explanations

    instances of first-person pronouns

    oai_token-act-pair · gemini-2.0-flash

    first-person plural pronouns

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

    we

    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
    RuleContext
    -0.55
     SqlConnection
    -0.52
     Pliny
    -0.51
    TestBed
    -0.50
     forskj
    -0.50
    LookAnd
    -0.49
    hilangan
    -0.49
    津
    -0.48
    ämie
    -0.48
     Lakeland
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.62
     utafitiHapana
    0.60
    νώ
    0.57
     highly
    0.57
     thought
    0.55
     ويكيميديا
    0.53
    észetes
    0.52
     rang
    0.51
     loved
    0.51
    neau
    0.50
    Activations Density 0.619%

    No Known Activations