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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1358
    Prev
    Next
    INDEX
    Explanations

    statistical information, ordinals, and comparisons

    oai_token-act-pair · gemini-2.0-flash

    Occurrences and frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    NameInMap
    -0.59
    WithIOException
    -0.56
    Controllo
    -0.53
    PullParser
    -0.52
    __["
    -0.51
     CRUD
    -0.49
    PHONY
    -0.49
    enterOuterAlt
    -0.49
     Shutter
    -0.47
    TestingModule
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.54
     morire
    0.53
    IUrlHelper
    0.51
    +#+#
    0.51
     compagni
    0.51
    ביוגרפיה
    0.51
    TacToe
    0.50
     jScrollPane
    0.50
    isuus
    0.50
    شهاد
    0.50
    Activations Density 2.329%

    No Known Activations