© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12370
    Prev
    Next
    INDEX
    Explanations

    phrases related to changing one's mind or changing some information

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "change"

    np_token-act-pair-logits · gpt-4o-mini

    change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    dsl
    -0.55
     PyQt
    -0.55
    ReusableCell
    -0.54
    ✷
    -0.54
    zzleHttp
    -0.54
    }{*}{
    -0.53
    HostException
    -0.50
     QtCore
    -0.50
    ])));
    -0.50
     endfor
    -0.49
    POSITIVE LOGITS
    ModelAdmin
    0.55
    ///</
    0.54
    tagext
    0.53
    DrawerToggle
    0.53
     métiers
    0.52
     something
    0.51
     forms
    0.50
    Jeografia
    0.50
     degrés
    0.49
    市镇
    0.48
    Activations Density 4.296%

    No Known Activations