© 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. 12250
    Prev
    Next
    INDEX
    Explanations

    general pronouns and how they relate to others

    oai_token-act-pair · gemini-2.0-flash

    it

    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
     really
    -0.54
     gynhyrchwyd
    -0.53
     realy
    -0.52
    cheiben
    -0.51
    really
    -0.50
    بسم
    -0.49
     REALLY
    -0.48
     المكتبه
    -0.47
    cheibe
    -0.47
     Mudd
    -0.47
    POSITIVE LOGITS
    日閲覧
    0.68
    UnusedPrivate
    0.57
    存于互联网档案馆
    0.52
     >=",
    0.52
    TestingModule
    0.50
    ,'"
    0.50
    modelBuilder
    0.50
     (
    0.49
    __*/
    0.49
    BeginContext
    0.48
    Activations Density 3.644%

    No Known Activations