Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 759
    Prev
    Next
    INDEX
    Explanations

    tentative statements anticipating a particular outcome including words such as "possible," "evaluate," "outcome," "confirmed," "clarify," "should," and "needed."

    oai_token-act-pair · gemini-2.0-flash

    outcome or results

    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
    TypedDataSet
    -0.49
     invokingState
    -0.46
     launched
    -0.45
    })));
    -0.45
    loma
    -0.43
     overview
    -0.43
     Overview
    -0.42
    perma
    -0.42
     versa
    -0.41
     kasarigan
    -0.40
    POSITIVE LOGITS
     wikipagina
    0.68
    makeText
    0.67
    iseksi
    0.64
    期刊论文
    0.64
    matchCondition
    0.63
    省市镇
    0.63
    OOTDTY
    0.59
    PageRoute
    0.58
     debout
    0.58
     المعيارى
    0.58
    Activations Density 3.462%

    No Known Activations