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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3480
    Prev
    Next
    INDEX
    Explanations

    uses of the words "can", "that", "this", "fake", and "to"

    oai_token-act-pair · gemini-2.0-flash

    Detecting fake, fraud, deception

    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
     fake
    -2.17
     Fake
    -2.14
    Fake
    -2.08
    fake
    -1.97
    FAKE
    -1.81
     fakes
    -1.74
     Mock
    -1.72
     faking
    -1.71
     faked
    -1.70
    Mock
    -1.68
    POSITIVE LOGITS
     KeyEvent
    0.67
    SourceChecksum
    0.66
    uxxxx
    0.58
    PreferredItem
    0.58
    Subviews
    0.57
     '\\;'
    0.56
     TimeUnit
    0.56
     Boll
    0.56
    +#+#
    0.56
    KeySpec
    0.54
    Activations Density 3.177%

    No Known Activations