© 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. 4046
    Prev
    Next
    INDEX
    Explanations

    historical text referencing time periods or locations

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    ########.
    -0.64
    onAttach
    -0.59
    IBOutlet
    -0.53
    sbericht
    -0.51
    QRect
    -0.51
    estacks
    -0.49
     SqlParameter
    -0.48
    mybatisplus
    -0.47
     DBNull
    -0.47
    MOQ
    -0.47
    POSITIVE LOGITS
    ">//
    0.64
     الحره
    0.62
     épis
    0.56
     Muses
    0.53
    CppMethod
    0.53
     Diakses
    0.52
     daarbij
    0.52
     dedans
    0.52
     prochaines
    0.51
     oignons
    0.50
    Activations Density 9.394%

    No Known Activations