© 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. 8951
    Prev
    Next
    INDEX
    Explanations

    language related to cost savings and manufacturing improvements

    oai_token-act-pair · gemini-2.0-flash

    Reducing costs

    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
    +#+#
    -0.59
     للمعارف
    -0.52
    ).—
    -0.49
     nonatomic
    -0.49
    onCreate
    -0.49
    costs
    -0.49
    buttonBar
    -0.49
    iastical
    -0.47
    AutoScaleMode
    -0.47
    cost
    -0.46
    POSITIVE LOGITS
    principalColumn
    0.57
    abstractmethod
    0.54
    SequentialGroup
    0.53
    tinta
    0.51
    kloped
    0.50
    PageContext
    0.50
     Pingback
    0.49
    jspx
    0.48
    Rhestr
    0.48
    DrawerToggle
    0.48
    Activations Density 5.254%

    No Known Activations