© 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. 6591
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing uncertainty or qualification, and language frequently used in legal or official documents.

    oai_token-act-pair · gemini-2.0-flash

    Subjective descriptions

    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
    ChildScrollView
    -0.60
    Hochspringen
    -0.60
     Vikipedi
    -0.59
    verwijspagina
    -0.58
     disambiguazione
    -0.56
    stdc
    -0.54
     estekak
    -0.54
    ismet
    -0.54
    WebElementEntity
    -0.54
    fjspx
    -0.53
    POSITIVE LOGITS
    yntaxException
    0.59
    териалы
    0.54
     comigo
    0.52
    RegressionTest
    0.51
     Oyun
    0.51
     conmigo
    0.50
     ne
    0.50
    مصادر
    0.48
    Ten
    0.47
    me
    0.47
    Activations Density 8.540%

    No Known Activations