© 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. 7031
    Prev
    Next
    INDEX
    Explanations

    the characters "li"

    oai_token-act-pair · gemini-2.0-flash

    li

    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
    ########.
    -0.53
    DeleteBehavior
    -0.48
    ład
    -0.47
    stal
    -0.45
    brainly
    -0.45
    SourceChecksum
    -0.44
     saluti
    -0.42
    alyptus
    -0.41
    posedge
    -0.40
    లాలు
    -0.40
    POSITIVE LOGITS
    contentLoaded
    0.60
    AndroidJUnit
    0.60
     mergeFrom
    0.57
    itson
    0.57
    Hochspringen
    0.56
    NameInMap
    0.54
     defaultstate
    0.53
     propOrder
    0.52
     Theſe
    0.52
    mine
    0.52
    Activations Density 2.053%

    No Known Activations