© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11912
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to harm, danger, and accidents

    oai_token-act-pair · gemini-2.0-flash

    Period

    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
     '\\;'
    -0.49
    ]=>
    -0.49
    ereo
    -0.47
    ImageContext
    -0.46
    Насе
    -0.45
    __);
    -0.43
    binant
    -0.43
    FirstName
    -0.42
     Maynard
    -0.42
    Insp
    -0.41
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.72
     actionMode
    0.67
    actionMode
    0.64
    tisseur
    0.63
    bewerken
    0.61
     houſe
    0.60
    TestingModule
    0.59
    وزش
    0.57
     "..\..\..\
    0.57
    DockStyle
    0.56
    Activations Density 1.137%

    No Known Activations