© 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. 13555
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate alarm, fear, or anger

    oai_token-act-pair · gemini-2.0-flash

    negative emotions

    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
    vegli
    -0.43
     cela
    -0.39
    ocer
    -0.39
    []
    -0.38
     μον
    -0.38
     xung
    -0.38
     poliester
    -0.38
    ~
    -0.38
    yo
    -0.38
    quila
    -0.37
    POSITIVE LOGITS
     EconPapers
    1.24
    DockStyle
    0.84
    +:+
    0.82
    Portale
    0.81
    AndEndTag
    0.76
     intptr
    0.75
    évaluateur
    0.75
     <<<<<<<<<<<<<<
    0.74
    ftagPool
    0.74
    principalTable
    0.73
    Activations Density 0.569%

    No Known Activations