© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5170
    Prev
    Next
    INDEX
    Explanations

    language about helping people or providing service

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs

    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
    ρίς
    -0.55
     classica
    -0.54
     sending
    -0.53
    sent
    -0.53
    vänt
    -0.52
    AddTagHelper
    -0.50
    帖最后由
    -0.49
     Sending
    -0.49
     sent
    -0.49
    HasAnnotation
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    0.72
    NameInMap
    0.69
    __":
    0.65
    তথ্যসূত্র
    0.65
    </thead>
    0.62
    __':
    0.61
    //
    0.59
    prochen
    0.58
    tvguidetime
    0.57
    --*/
    0.56
    Activations Density 1.371%

    No Known Activations