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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11112
    Prev
    Next
    INDEX
    Explanations

    discussions about crime and criminals.

    oai_token-act-pair · gemini-2.0-flash

    negative events involving people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tagHelperRunner
    -0.73
    reportWebVitals
    -0.72
    featureID
    -0.68
     AttributeSet
    -0.64
    原始内容存档于
    -0.64
     "..\..\..\
    -0.63
     PATENT
    -0.59
     "..\..\
    -0.58
    numerusform
    -0.58
     <<<<<<<<<<<<<<
    -0.57
    POSITIVE LOGITS
     gu
    0.52
    ècie
    0.50
     يتيمه
    0.49
    curity
    0.46
    einander
    0.44
     pourtant
    0.43
    fromnode
    0.43
     operativos
    0.42
    organizzazione
    0.41
    styleUrls
    0.41
    Activations Density 1.571%

    No Known Activations