© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1010
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to physical violence and confrontation

    oai_token-act-pair · gemini-2.0-flash

    say "with/his/its [adjective]..."

    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
    less
    -0.45
     comprende
    -0.44
    ：
    -0.40
    ."<
    -0.40
     :
    -0.40
     Monfieur
    -0.38
    }(),
    -0.38
     =
    -0.38
    :</
    -0.38
    }){
    -0.38
    POSITIVE LOGITS
    UrlResolution
    0.78
     otomatig
    0.72
    ChildScrollView
    0.71
    atellite
    0.70
    InitVars
    0.70
    AsUp
    0.69
    EFAULT
    0.69
     fieldNum
    0.69
    onActivityResult
    0.68
    TemporalType
    0.66
    Activations Density 3.959%

    No Known Activations