© 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. 1358
    Prev
    Next
    INDEX
    Explanations

    the word "on" and related prepositions and articles

    oai_token-act-pair · gemini-2.0-flash

    on

    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
    новниш
    -0.70
    Rhestr
    -0.64
    setVerticalGroup
    -0.60
    AddHtmlAttribute
    -0.59
    StoryboardSegue
    -0.57
    UrlResolution
    -0.52
    EndContext
    -0.51
    rungsseite
    -0.50
    lamic
    -0.49
    tagHelperRunner
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.66
    ligheten
    0.58
     connexe
    0.57
     LIRE
    0.52
    CppMethod
    0.52
    yyj
    0.51
     vana
    0.50
    イルド
    0.50
     Vial
    0.49
     Folks
    0.48
    Activations Density 2.897%

    No Known Activations