© 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. 8126
    Prev
    Next
    INDEX
    Explanations

    words related to formal documents about people, such as school and racing rosters.

    oai_token-act-pair · gemini-2.0-flash

    demographic data

    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
    اديم
    -0.47
    ;';
    -0.46
    ├──
    -0.45
    nlm
    -0.44
     शामिल
    -0.44
    munk
    -0.43
     Hid
    -0.42
    /$',
    -0.42
    ücksich
    -0.42
    ذا
    -0.42
    POSITIVE LOGITS
    GenerationType
    0.82
    IBOutlet
    0.77
    Datuak
    0.72
    DockStyle
    0.72
    ArgsConstructor
    0.71
    InjectAttribute
    0.68
     NSCoder
    0.68
    ngdoc
    0.68
    GEBURTSDATUM
    0.66
    LEncoder
    0.65
    Activations Density 19.064%

    No Known Activations