© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6995
    Prev
    Next
    INDEX
    Explanations

    uses of the word "to" in a variety of contexts.

    oai_token-act-pair · gemini-2.0-flash

    Understanding

    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
     dig
    -0.80
    dig
    -0.59
     Dig
    -0.52
    OWA
    -0.52
    αιν
    -0.50
    omeness
    -0.50
    sság
    -0.49
    NHL
    -0.47
    osoba
    -0.47
    jstor
    -0.46
    POSITIVE LOGITS
     HasFactory
    0.66
     виправивши
    0.59
     polvere
    0.58
    yntaxException
    0.56
     ModelAndView
    0.54
    auté
    0.53
    MigrationBuilder
    0.51
    verwijspagina
    0.50
    省市镇
    0.50
     NavController
    0.50
    Activations Density 8.483%

    No Known Activations