© 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. 10847
    Prev
    Next
    INDEX
    Explanations

    descriptions of the interiors of old buildings

    oai_token-act-pair · gemini-2.0-flash

    words related to architectural features

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

    Ceilings and lights

    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
    expandindo
    -0.53
     виправивши
    -0.52
    PreferredItem
    -0.51
     tartalomajánló
    -0.51
    rzost
    -0.48
    SharedCtor
    -0.48
    UnusedPrivate
    -0.47
    равда
    -0.47
     vice
    -0.45
    PathVariable
    -0.45
    POSITIVE LOGITS
    LLocation
    0.65
    pfung
    0.55
    jsonwebtoken
    0.54
     initComponents
    0.54
    spotted
    0.52
    PageFactory
    0.52
    Données
    0.51
    esez
    0.48
     tongues
    0.48
     HasFactory
    0.48
    Activations Density 0.823%

    No Known Activations