© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12678
    Prev
    Next
    INDEX
    Explanations

    words and short clauses involving past tense verbs that describe someone discovering or observing something

    oai_token-act-pair · gemini-2.0-flash

    Actions and verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    xie
    -0.46
    <eos>
    -0.45
     au
    -0.45
     
    -0.45
    <bos>
    -0.43
    ÍN
    -0.43
     [
    -0.42
    pheny
    -0.42
     ap
    -0.42
    anks
    -0.42
    POSITIVE LOGITS
     nahilalakip
    1.03
     كومونز
    1.00
    Portale
    0.92
    ⓧ
    0.92
     myſelf
    0.84
     ſtate
    0.83
     purpoſe
    0.82
     uſe
    0.81
     greateſt
    0.81
     fhort
    0.81
    Activations Density 0.908%

    No Known Activations