© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4336
    Prev
    Next
    INDEX
    Explanations

    text related to fashion styling and how to create different looks

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    OGND
    -0.91
     nahilalakip
    -0.89
    AndEndTag
    -0.85
    AddTagHelper
    -0.84
    ContentAsync
    -0.82
     kaarangay
    -0.79
     resourceCulture
    -0.78
     Normdatei
    -0.77
     @"/
    -0.76
    unknownFields
    -0.75
    POSITIVE LOGITS
    kriegs
    0.42
    Listeners
    0.42
     TUT
    0.40
     loggedIn
    0.40
    Jeez
    0.40
    っかり
    0.40
    gnac
    0.39
    ́t
    0.39
    patri
    0.39
     pair
    0.38
    Activations Density 6.066%

    No Known Activations