© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12025
    Prev
    Next
    INDEX
    Explanations

    phrases where many instances of the word "more" or "less" occur in a small window

    oai_token-act-pair · gemini-2.0-flash

    comparisons involving more/less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    __":
    -0.93
    Personensuche
    -0.89
    yntaxException
    -0.84
    AndEndTag
    -0.84
    __":
    -0.83
    SharedDtor
    -0.82
    SequentialGroup
    -0.82
     Administrativna
    -0.77
    rrggbb
    -0.76
    CppMethod
    -0.75
    POSITIVE LOGITS
    ead
    0.47
     Direct
    0.45
    theim
    0.45
     direct
    0.45
    ाइ
    0.44
     Stück
    0.44
    rét
    0.43
    entially
    0.43
    Http
    0.43
     jagung
    0.42
    Activations Density 0.624%

    No Known Activations