© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8341
    Prev
    Next
    INDEX
    Explanations

    words that usually appear in lists like prepositions, conjunctions, and pronouns

    oai_token-act-pair · gemini-2.0-flash

    religious discussions

    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
    stdafx
    -0.55
     élevées
    -0.50
     picioare
    -0.49
     poupée
    -0.47
     réglable
    -0.46
     suministros
    -0.46
    kovo
    -0.45
     bandoulière
    -0.44
     conferencia
    -0.44
    ার্
    -0.44
    POSITIVE LOGITS
    ChildScrollView
    0.79
     onPostExecute
    0.77
    GEBURTSDATUM
    0.66
     Roskov
    0.66
    Hochspringen
    0.65
    WriteAttribute
    0.63
    DispatchToProps
    0.63
    InjectMocks
    0.62
    ReusableCell
    0.60
    ViewImports
    0.59
    Activations Density 9.302%

    No Known Activations