© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2715
    Prev
    Next
    INDEX
    Explanations

    a mix of code, lists of location words and security authentication terms

    oai_token-act-pair · gemini-2.0-flash

    Miscellaneous system information

    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
    chromosome
    -0.71
    anniversary
    -0.69
     honeymoon
    -0.67
    segmentation
    -0.66
     centenary
    -0.65
     manslaughter
    -0.65
     chromosome
    -0.65
     rheumatism
    -0.64
    DECLARATION
    -0.64
    marathon
    -0.64
    POSITIVE LOGITS
     key
    0.68
     sound
    0.67
     art
    0.64
    key
    0.64
     الرياضيه
    0.63
    aarrggbb
    0.63
    text
    0.61
    ops
    0.59
     text
    0.57
     press
    0.57
    Activations Density 9.841%

    No Known Activations