© 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. 15458
    Prev
    Next
    INDEX
    Explanations

    the prefix "lo" followed by a hyphen or other characters

    oai_token-act-pair · gemini-2.0-flash

    lo

    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
    లాలు
    -0.64
     wireType
    -0.64
     '\\;'
    -0.62
    AndEndTag
    -0.61
    :✨
    -0.60
    MLLoader
    -0.58
    ########.
    -0.57
    цездатний
    -0.57
    DeleteBehavior
    -0.57
     aDecoder
    -0.57
    POSITIVE LOGITS
    PRI
    0.51
    vero
    0.50
     []:
    0.47
    TargetApi
    0.47
    penny
    0.45
    OptionsMenu
    0.44
     ví
    0.43
    изо
    0.43
    出版年
    0.43
    ABI
    0.43
    Activations Density 3.055%

    No Known Activations