© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13019
    Prev
    Next
    INDEX
    Explanations

    words or phrases about a short restful period in a place, or about confrontations

    oai_token-act-pair · gemini-2.0-flash

    stay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    numerusform
    -0.86
     noDo
    -0.77
    Anhalt
    -0.76
    Fuckin
    -0.74
     للمعارف
    -0.72
    elsif
    -0.68
    DOCTYPE
    -0.68
     Bioaccumulative
    -0.68
    RUnlock
    -0.67
    obacterium
    -0.66
    POSITIVE LOGITS
    <bos>
    0.82
     løpet
    0.53
     the
    0.45
    oa̍t
    0.44
     París
    0.44
     meninas
    0.44
     veiks
    0.44
     Grecs
    0.44
     hvem
    0.43
     nemici
    0.43
    Activations Density 1.450%

    No Known Activations