© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13961
    Prev
    Next
    INDEX
    Explanations

    references to historical places and people, especially names ending in 'mas', tribal affiliations, and locations in ancient geography.

    oai_token-act-pair · gemini-2.0-flash

    historical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Rüyada
    -0.31
    DIPSETTING
    -0.30
     AssemblyCulture
    -0.30
    delwed
    -0.27
     at
    -0.27
     de
    -0.26
     les
    -0.26
    TagMode
    -0.25
     IT
    -0.24
     e
    -0.24
    POSITIVE LOGITS
     Theſe
    0.98
     purpoſe
    0.95
     itſelf
    0.94
     pleaſure
    0.92
     Houſe
    0.91
     Majefty
    0.90
     Diſ
    0.90
     Monfieur
    0.90
     raiſ
    0.90
     becauſe
    0.90
    Activations Density 24.556%

    No Known Activations