© 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. 12219
    Prev
    Next
    INDEX
    Explanations

    phrases that represent a negative connotation

    oai_token-act-pair · gemini-2.0-flash

    caution/avoidance

    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
    <bos>
    -0.63
     Femen
    -0.56
    ьаж
    -0.52
     Wikiquote
    -0.52
     ThemeData
    -0.51
    istani
    -0.49
     Himself
    -0.48
    WriteTagHelper
    -0.48
     aught
    -0.48
    timation
    -0.47
    POSITIVE LOGITS
    ReusableCell
    0.68
    stdc
    0.64
    CppMethod
    0.56
     ComVisible
    0.52
    ArgsConstructor
    0.49
    tał
    0.49
     autorytatywna
    0.48
     mergeFrom
    0.48
    glLoadIdentity
    0.47
    fromnode
    0.47
    Activations Density 0.550%

    No Known Activations