© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9889
    Prev
    Next
    INDEX
    Explanations

    words and phrases signifying positive experiences and recommendations

    oai_token-act-pair · gemini-2.0-flash

    Positive experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     كومونز
    -0.80
    SequentialGroup
    -0.78
    TagMode
    -0.76
     متعلقه
    -0.75
     kaarangay
    -0.67
    Personendaten
    -0.65
    ंदीखरीदारी
    -0.63
    InitVars
    -0.63
    FunctionFlags
    -0.63
     lenker
    -0.63
    POSITIVE LOGITS
    r
    0.47
    Mem
    0.45
     parad
    0.44
     Jim
    0.42
     joyous
    0.42
     most
    0.42
     magical
    0.41
     Mem
    0.41
    APA
    0.40
    springframework
    0.39
    Activations Density 0.670%

    No Known Activations